This study explores novel techniques to improve the detection accuracy of skarn iron deposits using advanced image processing methodologies. Leveraging the capabilities of Aster image, Band Ratio (BR) images, and Principal Component Analysis (PCA), alongside the power of 3D Convolutional Neural Networks (3D-CNN), the research aims to enhance the precision and efficiency of ore detection in complex geological environments. The proposed method employs a specific 3D-CNN architecture, accepting input as a 7×7×C image patch, where C represents the combined number of selected Aster image bands, Principal Component (PC) bands, and computed BR images. To evaluate the accuracy of the proposed method, five distinct image bands combinations, including the proposed bands combination, were tested and evaluated based on the overall accuracy (OA), average accuracy (AA), and kappa coefficient. The results demonstrated that while the incorporation of BR images alongside Aster bands initially seemed promising, it introduced significant confusion in certain classifications, leading to unexpected mis-classification rates. Surprisingly, utilizing solely Aster bands as input parameters yielded higher accuracy rates (OA= 93.13%, AA = 91.96%, Kappa = 90.91%) compared to scenarios involving the integration with band ratios (OA = 87.02%, AA = 79.15, and Kappa = 82.60%) or the integration of BR images to PC bands (OA= 87.78%, AA = 82.39%, Kappa = 83.81%). However, the amalgamation of Aster bands with selected PC bands showed slight improvements in accuracy (OA= 94.65%, AA = 92.93%, Kappa = 93.45%), although challenges in accurately classifying certain features persisted. Ultimately, the proposed combination of Aster bands, PC bands, and BR images (proposed bands combination) presented the most visually appealing and statistically accurate results (OA = 96.95%, AA= 94.87%, and Kappa = 95.93%), effectively addressing misclassifications observed in the other combinations. These findings underscore the synergistic contributions of each of the Aster bands, PC bands, and BR images, with Aster bands proving pivotal for optimal skarn classification, PC bands enhancing intrusions classification accuracy, and BR images strengthening wall rock classification accuracy. In conclusion, the proposed combination of input image bands emerges as a robust and comprehensive methodology, demonstrating unparalleled accuracy in the remote sensing detection of skarn iron minerals.

This paper proposed emotion recognition methods for consecutive facial images, and implements the inference of neural network model on a field-programmable gate array (FPGA). The proposed emotion recognition methods are based on a neural network model architecture that combines convolution neural networks (CNNs), long short-term memory (LSTM), and fully connected neural networks (FCNNs), called CLDNN or ConvLSTM-FCN. This type of neural network mod-el can analyze the local feature sequences obtained through convolution of data, making it suita-ble for processing time-series data such as consecutive facial images. In this paper, sequences of facial images are sampled from videos corresponding to various emotional state of subjects. The sampled images are then pre-processed with the processes includes facial detection, greyscale conversion, resize, and data augmentation if necessary. The 2-D CNN in ConvLSTM-FCN is used for feature extraction for these pre-processed facial images. These sequences of facial im-age features are time sequences with dependent properties between the elements within them. The LSTM is then used to model these time sequences followed by fully connected neural net-works (FCNNs) for classification. The proposed consecutive facial emotion recognition method achieves an average recognition rate of 99.51% on RAVDESS dataset, 87.80% on BAUM-1s dataset and 96.82% on eNTERFACE’05 data set, using 10-fold cross-validation on the PC. Some com-parisons of recognition accuracies between the proposed method and the other existing related works are conducted in this paper. According to the comparisons, the proposed emotion recog-nition methods outperform the existing related researches. The proposed emotion recognition methods are then implemented on an FPGA chip using the neural network model inference algo-rithms in this paper, and the accuracies of the experiments conducted on the FPGA chip are iden-tical to those obtained on the PC. This verifies that the proposed neural network model imple-mented on the FPGA chip performs well.

(1) Background: The aim of the research was to present and emphasize the importance of magnetic resonance imaging (MRI) in diagnosing Achilles tendon (AT) ruptures by presenting case reports. (2) Materials and Methods: The sample of respondents included 7 patients (4 males and 3 females, 2 athletes and 5 non-athletes), aged 25 to 58 years, with AT injuries, who were examined and treated at the Institute for Treatment and Rehabilitation "Niška Banja", Niš, Serbia. Ankle examinations with MRI were conducted using the Esaote O-scan 0.3 T machine. The examinations were performed without the application of a paramagnetic contrast agent and without the use of anesthesia. Results: The MRI method's sensitivity and overall diagnostic accuracy were excellent, with 100% true positives. In our study, the method accurately detected the presence, location, and severity of AT injuries in all cases. MRI is an important and reliable method for detecting AT injuries, classifying them, monitoring the course of recovery, and assessing the effects of therapy. Conclusions: An unrecognized or delayed diagnosis of an AT injury can lead to chronic changes. Timely diagnosis (clinical examination, ultrasonography, magnetic resonance imaging) and appropriate treatment (conservative or operative) enable patients to return to normal activities, including sports. Unfortunately, the use of MRI is limited by restricted access and the cost of the examination.

Using UAV-based multispectral images for quickly and accurately monitoring chlorophyll content is critical for field management and yield estimation. However, the lower model accuracy and the poor robustness of the estimation models are still preventing the widespread application of UAV-based multispectral images. We carried out two field trials at various experimental sites to further enhance the precision and applicability of the model used to estimate the chlorophyll content of potato plants. Firstly, the texture features and vegetation indices derived from multispectral images were screened using the Pearson correlation coefficient method, and Normalized difference red edge (NDRE) performed the best over the two growth periods. Secondly, principal component analysis (PCA) was applied to recombine five bands of multispectral images, and third PCA results (PCA3) was selected to combined with NDRE according to the construction principle of NDRE, and the newly constructed parameter was named improved NDRE (INDRE). Finally, INDRE was used to establish a chlorophyll content estimation model of potato plants, and compared with some traditional parameters. The results demonstrated that the INDRE had the maximum accuracy (R2 = 0.7865, RMSE = 2.1378), and corresponding R2 increased by 0.1481 and RMSE decreased by 1.2994 than NDRE. Additionally, the model was validated using independent data from Experiment 2, and INDRE considerably increased estimation accuracy compared to other factors. In conclusions, the INDRE suggested in this study significantly enhances the accuracy and applicability of the chlorophyll content inversion model and can serve as an additional reference for fertilization management.

Change Detection (CD) of aerial images refers to identifying and analyzing changes between two or more aerial images of the same location taken at different times. The CD is a highly challenging task due to the need to distinguish relevant changes, such as urban expansion, deforestation, or post-disaster damage assessment, from irrelevant ones, such as light conditions, shadows, and seasonal variations. Many CD papers have recently been published, where most of the papers that proposed a new model contained a comparison between their proposed and state-of-the-art (SOTA) models. While many recent studies propose new deep learning (DL) models for improving CD performance, their comparative analyses are often restricted, lacking comprehensive insights into the proposed models' real-world generalizability, robustness, and performance trade-offs across diverse change characteristics. This paper presents a novel generic framework to systematically benchmark and assess DL-based CD models through three parallel pipelines: 1) cross-testing models on diverse benchmark datasets to evaluate generalization, 2) robustness analysis against different image corruptions, and 3) multi-faceted contour-level analytics evaluating detection sensitivity to change size/complexity. The framework is applied to comparatively evaluate five state-of-the-art DL-based CD models - Changeformer, BIT, Tiny, SNUNet, and CSA-CDGAN. Extensive experiments unveil each model's strengths, limitations and biases, highlighting their relative proficiencies in generalizing across data distributions, resilience to noise corruption, and discriminative capabilities for changes of varying characteristics. The proposed benchmarking framework demonstrates significant potential for guiding the selection of suitable CD models tailored to specific application requirements by comprehensively evaluating their generalizability, robustness, and detection capabilities across diverse real-world scenarios. This systematic evaluation approach can drive future research into developing more robust and versatile CD solutions aligned with practical needs.

This study introduces SkinLiTE, a lightweight supervised contrastive learning model, tailored to enhance the detection and typification of skin lesions in dermoscopic images. The core of SkinLiTE lies in its unique integration of supervised and contrastive learning approaches, which leverages labeled data to learn generalizable representations. This approach is particularly adept at handling the complexities and imbalances inherent in skin lesions datasets. The methodology encompasses a two-phase learning process. In the first phase, SkinLiTE utilizes an encoder network and a projection head to transform and project dermoscopic images into a feature space where contrastive loss is applied, focusing on minimizing intra-class variations while maximizing inter-class differences. The second phase freezes the encoder's weights, leveraging the learned representations for classification through a series of dense and dropout layers. The model was evaluated using three datasets from Skin Cancer ISIC 2019-2020, covering a wide range of skin conditions. SkinLiTE demonstrated superior performance across various metrics—accuracy, AUC , and F1 score—particularly when compared with traditional supervised learning models. Notably, SkinLiTE achieved an accuracy of 0.9087 using AugMix augmentation for binary classification of skin lesions. It also showed comparable results with the state-of-the-art approaches of ISIC challenge without relying on external data, underscoring its efficacy and efficiency. The results highlight the potential of SkinLiTE as a significant step forward in the field of dermatological AI, offering a robust, efficient, and accurate tool for skin lesion detection and classification. Its lightweight architecture and ability to handle imbalanced datasets make it particularly suited for integration into Internet of Medical Things environments, paving the way for enhanced remote patient monitoring and diagnostic capabilities. This research contributes to the evolving landscape of AI in healthcare, demonstrating the impact of innovative learning methodologies in medical image analysis.

Accurate detection of forest restoration sites using deep learning is crucial for effective ecosystem management, optimizing reforestation efforts, and ensuring environmental sustainability. While various deep learning-based systems have been developed for this purpose, the influence of different neural network architectures on model performance during the identification of forest restoration sites remains underexplored. This study aimed to address this gap by exploring the optimal methodology for extracting and classifying candidate sites for forest restoration based on Convolutional Neural Networks (CNNs), specialized for image recognition. Four categories—arable land, road and barren, quarry, and forest—were defined as candidate sites for forest restoration. A dataset comprising 17,043 samples was divided into training (11,929) and validation (5,114) sets at a ratio of 7:3 for model learning. Model accuracy was evaluated using pixel accuracy (PA) and mean intersection over union (mean IoU). The Resnet152-U-Net model demonstrated a pixel accuracy of 95.2% and a mean IoU of 61.3%, indicating excellent performance in extracting candidate sites for forest restoration. This approach offers spatial and temporal advantages over conventional field surveys or aerial image-based assessments, potentially serving as valuable data for selecting future forest restoration sites.

Byers Peninsula (62°34’-62°40’S-60°54’61°13’W), 60 km2 in size, is considered one of the largest ice-free areas in Antarctica. Since 2006, the Spanish Polar Program has taken part in a large number of environmental studies involving effects of climate changes, limnology and microbiology, live cycles, but not albedo. Surface albedo is one of the key physical parameters in the surface energy budget of polar regions. Most of Antarctica is covered by ice sheets; only about 0.44% of the area is permanently ice-free. However, in maritime Antarctica, the ice-free areas, corresponding to small islands, peninsulas, and coastal beaches, account for about 3% of the territory. To incorporate the contribution of these areas into global albedo models, it is necessary to relate the soil properties of the ice-free areas to the surface albedo response. Also, mapping soil properties and albedo have and special interest in these ice-free areas. Image classification using machine learning methods trained with georeferenced soil data could be useful for mapping soil properties and albedo in multispectral optical satellite images. A shallow neural network implemented using the Keras Python module was used to define and train models of soil properties using 15 explanatory variables corresponding to bands and spectral indices of a Sentinel image and a population of 49 soil samples taken from the top 5 centimeters of the soil profile. The soil samples were analyzed in the laboratory and a spectral library in the Vis-Nir range (350-2500 nm) was created. The albedo of the samples was integrated from the ADS spectra. At the same time, a linear regression model of albedo using the soil properties as explanatory variables was performed. The R2 fit of this new model was about 0.82 and the error of estimation was 4.1. The model was extended to the entire Byers Peninsula using the ML soil property models as explanatory variables. The RMSE of the extended models increased up to 8.2. We think that the main cause of this increase (2.6 points) is related to the error propagation, phenomenon due to the use of models as explanatory variables. However, another important part of the error increase could be due, among other reasons, to the use of an image that, although corrected, is not completely free of clouds.

Byers Peninsula is considered one of the largest ice-free areas in Maritime Antarctica. Since 2006, the Spanish Polar Program has taken part in a large number of environmental studies involving effects of climate changes in lives cycles, limnology and microbiology. Soils from maritime Antarctica are generally weakly developed and have chemical, physical and morphological characteristics strongly influenced by the parent material. However, biological activity during the short Antarctic summer promotes intense transference of nutrients and organic matter in areas occupied by different species of birds and marine mammals. To mapping and monitoring those areas with high biological occupation, could be very useful to have models of edaphic properties prepared from satellite images. In this approach, Deep Learning and Linear Regression models of soil properties and spectral indexes as explicative variables were performed. We training models of soil properties closely related to biological activity such as Dissolved Organic Carbon (DOC) and the iron fraction associated with organic matter (Fe). We tested the best approach to model the spatial distribution of DOC, Fe and pH by training models of Linear Regression and Deep Learning over Sentinel2 and WorldView2 images. The most robust models were used to track possible areas with ornithogenic soils as well as areas of the Byers Peninsula that could support the highest biological development.

Yield calculation is an important link in modern precision agriculture, which is an effective means to improve breeding efficiency, and adjust planting and marketing plans. With the continuous progress of artificial intelligence and sensing technology, yield calculation schemes based on image processing technology have many advantages such as high accuracy, low cost, and non-destructive calculation, and have been favored by a large number of researchers. This article reviews the research progress of crop yield calculation based on remote sensing images and visible light images, describes the technical characteristics and applicable objects of different schemes, and focuses on detailed explanations of data acquisition, independent variable screening, algorithm selection and optimization. Common issues are also discussed and summarized. Finally, solutions are proposed for the main problems that have arisen so far, and future research directions are predicted, with the aim of achieving more progress and wider popularization of yield calculation solutions based on image technology.

Measuring and predicting Carbon Emission (CE) is important to enabling the main culprit of various urgent environmental issues including global warming. However, prior studies did not fully incorporate the impact of micro-level urban streetscapes, which might lead to biased prediction of urban CE. To fill the gap, we developed an effective framework to predict residential CE in urban areas from widely existing and publicly available street-view images (SVI) using machine learning. First, we used a semantic segmentation algorithm to classify more than 30 streetscape elements from SVI images to describe the built environment whose features might affect residential and transportation CE. Second, based on the streetscapes quantified, we trained a 10-fold cross-validation method with various machine learning models to predict the CE at the 1KM grid level using CE data from the PlanetData. We found first, built environment features such as sidewalks, roads, fences, buildings, and walls are significantly correlated with the residential CE. Second, the presence of buildings and subtle streetscape features (e.g., walls, fences) indicates higher-density residential areas which are related to more residential CE. Third, vegetation (e.g., trees and grass) are reversely related to residential CE. Our findings shed light on the feasibility of using a single and open data source (i.e., the SVI) to effectively model neighborhood-level CE for regions across diverse urban forms. Our framework is useful for urban planners to inform new town development and urban regeneration towards the low CE goals.

This research delves into the intricate challenges confronting the agricultural sector, with a specialized focus on mitigating infections in tomato crops, particularly powdery mildew induced by the Leveillula Taurica pathogen. Tomatoes, renowned for their nutritional richness, are vital to global food security. However, conventional methodologies for disease detection exhibit both laborious processes and limited accuracy. In response to these challenges, this study advocates for an innovative fusion of hyperspectral imaging and deep learning methodologies to detect crop disease and its severity. The systematic workflow commenced with the curation of a dataset, involving the acquisition of live images through OpenCV, followed by conversion to RGB format and subsequent feature extraction utilizing a pre-trained visual geometry group (VGG-16) model for enhanced analysis. Sequentially, RGB images were transformed into simulated hyperspectral images (SHSI) leveraging a Neural Network generator model, offering a distinctive viewpoint on spectral information. This novel approach transcends conventional constraints by delivering a three-dimensional perspective, seamlessly integrating spatial and spectral dimensions for holistic data acquisition. The SHSI is further transmuted into a 3D visualization cube comprehensive grasp of spatial and spectral aspects encompassing spectral, spatial, and Haralick features. The research concludes with severity detection, categorized as low, moderate, or high, employing a Gaussian Mixture Model (GMM) and K-means for visualization.

Document image binarization is a challenging task, especially when it comes to text segmentation in degraded document images. The binarization, as a pre-processing step of optical character recognition (OCR), is one of the most fundamental and commonly used segmentation methods. It separates the foreground text from the background of the document image to facilitate subsequent image processing. In view of the different degradation degree of document image, researchers have proposed a variety of solutions. This paper reviews the main binarization techniques, including both traditional algorithms and deep learning-based algorithms. We also summarize some difficulties and challenges in the field of document image binarization. Here, we evaluate various image binarization techniques to identify shortcomings in current methods and provide some help for future research.

The capability of in-house transient wave-multibody computational tool of ITU-WAVE are extended to predict the wave power absorption with Wave Energy Converters (WECs) arrays placed in front of a vertical breakwater. The analyses of hydrodynamic exciting and radiation forces are approximated solving boundary integral equation at each time interval. The reflection of incoming waves due to a vertical wall is predicted with method of images. The constructive or destructive performance of WECs arrays with different array configurations is measured with mean interaction factor. The behaviour of the exciting and radiation hydrodynamic forces of each WEC due to a vertical wall effect shows considerable differences than those of WECs arrays without a vertical wall influence. When the wave power absorption with WECs arrays with and without a vertical wall effect are compared, it is shown with numerical experiences that WECs placed in front of a vertical wall have much greater effects on wave power absorption. This can be attribute to the hydrodynamic interaction, standing waves, and nearly trapped waves in the gap between a vertical wall and WECs arrays. The analytical and other numerical results are used to for the validation of the numerical results of the present ITU-WAVE computational tool for exciting and radiation forces, and mean interaction factor of WECs arrays which show satisfactory agreements.

Street view images can help us better understand the city environment and potential characteristics. With the development of computer vision and deep learning, the technology of semantic segmentation algorithms has become more mature. However, DeeplabV3+, which is commonly used in semantic segmentation, has shortcomings such as a large number of parameters, high requirements for computing resources, and easy loss of detailed information. Therefore, this paper proposes LM-DeeplabV3+, which aims to greatly reduce parameters and computations of the model while ensuring the segmentation accuracy. Firstly, the lightweight network MobileNetV2 is selected as the backbone network, and the ECA attention mechanism is introduced after MobileNetV2 extracts shallow features to improve the ability of feature representation; secondly, the ASPP module is improved, and on its basis, the EPSA attention mechanism is introduced to achieve cross-dimensional channel attention and important feature interaction; thirdly, a loss function named CL loss is designed to balance the training offset of multiple categories and better indicate the segmentation quality. This paper conducted experimental verification on the Cityspaces dataset, and the results showed that the mIoU reached 74.9%, which was an improvement of 3.56% compared to DeeplabV3+; the mPA reached 83.01%, which was an improvement of 2.53% compared to DeeplabV3+.

Remotely sensed data acquired by multispectral sensors can be used to monitor soil moisture (SM) across a larger land area than in situ monitoring alone. Although there have been wide-ranging applications of remote sensing tools in SM estimation on many ecosystems, there is a limited understanding of their accuracy in restored wetlands. The objective of this study was to examine the potential of remotely sensed data from Landsat-9, Sentinel-1A SAR, and Blackswift E2 Uncrewed Aircraft Systems (UAS) in predicting SM in a restored wetland complex in the Gunnison Basin of Colorado. We tested two response variables, gravimetric SM and volumetric SM, to determine which indicator of SM was better predicted with remotely sensed data. We also tested the accuracy of remotely sensed data in predicting SM at different soil depths. Overall, satellite and UAS indices predicted gravimetric SM better than volumetric SM. The Normalized Difference Red Edge (NDRE) index from Blackswift E2 UAS had the best prediction of GSM at the depth of 0 to 5 cm (R2 = 0.86, RMSE = 7.41). Results from the study provide information on the accuracy of remotely sensed data for SM monitoring on restored wetlands.

Immunohistochemistry is a powerful technique, widely used in biomedical research and clinics, that allows to determine the expression levels of some proteins of interest in tissue samples by means of the intensity of color due to the expression of biomarkers using specific antibodies. As such, immunohistochemical images are complex and problematic to be quantified. Recently we proposed a novel method including a first separation stage based on nonnegative matrix factorization (NMF) that achieved good results. However, that method was highly dependent on sparseness and non-negativity parameter choice and on algorithm initialization. Furthermore, the previously proposed method needed a reference image as starting point for the NMF algorithm. In the present work, we propose a new, simpler and robust method for the automated unsupervised scoring of immunohistochemical images based on bright field. Our work is focused on images from tumor tissues marked with blue (nuclei) and brown (protein of interest). The new proposed method represents a simpler approach that, in one side, avoids the use of NMF for the separation stage, and in the other side, circumvents the need for a control image. This new approach determines the subspace spanned by the two colors of interest by means of principal component analysis (PCA) with dimension reduction. This subspace is a two-dimensional space, allowing the finding of color vectors by considering the peaks of density of points. The method also develops a new scoring stage by avoiding, again, reference images, making the procedure more robust and less dependent on the parameters. Experiments for the semi-quantitative scoring of images in five categories exhibit promising and consistent results when compared to manual scoring carried out by experts.

Accurate geometric modeling of blood vessels lumen given their 3D images is a basis for vessel quantification in support of cardiovascular diseases diagnosis, treatment and monitoring. Unlike other approaches, which assume circular or elliptical vessel cross-section, the proposed method employs parametric B-splines combined with the image formation system equations to accurately localize the highly curved lumen boundaries. No image segmentation is involved which might reduce the localization accuracy in effect of spatial discretization. It is shown that the model parameters can be reliably identified by a feedforward neural network which, driven by the cross-section images, predicts the parameter values many times faster than a reference least-squares (LS) model fitting algorithm. Two example applications: modeling the lower extremities artery-vein complexes visualized in steady-state contrast-enhanced magnetic resonance images (MRI) and the coronary arteries pictured in computed tomography angiograms (CTA), are presented and discussed to demonstrate the method potential. Besides application to medical diagnosis, blood-flow simulation and vessel-phantom design, it can serve as a tool for automated annotation of image datasets required to train machine-learning algorithms.

X-band marine radar captures signal reflected from the sea surface. Theoretical studies indicate that the initial unfiltered signal contains meaningful information including parameters related to wind waves. Traditional methods for estimating significant wave height (SWH) rely on the physical laws describing signal reflection from rough surfaces. However, recent studies suggest the feasibility of employing artificial neural networks (ANNs) for SWH approximation. Both classical and ANN-based approaches necessitate costly in situ data. In this study, we propose generating synthetic radar images with specified wind wave parameters using Fourier-based approach and Pierson–Moskowitz wave spectrum as a viable alternative. We generate synthetic images and use them for unsupervised learning approach to train a convolutional component of an ANN. After that, we train a regression ANN based on the previous convolutional component to obtain SWH back from synthetic images. Then, we apply preliminary trained weights for the same regression model to train SWH approximation on the dataset of real sea clutter images. In this study, we demonstrate the increase in the accuracy of SWH estimation from radar images with the preliminary training on synthetic data.

Detecting rotated objects in remote sensing images poses a substantial challenge. These images usually cover a wide field of view, containing diverse and complex backgrounds with variously sized ground objects densely distributed. Therefore, identifying objects of interest in remote-sensing images is challenging. While integrating Convolutional Neural Networks (CNNs) and Transformer networks has exhibited progress in detecting rotated objects, there is still scope for enhancing feature extraction and fusion. To address this issue, we propose a feature extraction module, a feature context aggregation module, and a multi-scale feature fusion module. Initially, we substitute the Spatial Pyramid Pooling Bottleneck (SPPFBottleneck) with a new module aimed at extracting multi-scale features, thereby enhancing the detection of small objects in complex backgrounds. Next, we develop a novel module for the multi-scale fusion of contextual information within feature maps, extracting valuable information. Finally, we combine the original features with the fused ones to prevent the loss of specific features in the fusion process. We refer to our newly proposed model as the "Multi-scale Feature Context Aggregation Network" (MFCANet). We assess our approach on three challenging remote sensing datasets: MAR20, SRSDD, and HRSC. Comprehensive experimental results show that our method surpasses baseline models by 2.13%, 10.28%, and 1.46% mAP on the MAR20, SRSDD, and HRSC datasets, respectively.

Jalapeño peppers (Capsicum annuum L.) are an important agricultural product worldwide. Despite its high demand in recent years, there are few studies on its production under adverse conditions caused by environmental phenomena. Crops in protected environments such as aeroponics offer greater control of these phenomena and enable efficient use of resources. However, it is necessary to validate the cultivation technique for which new technologies are being used. One of these is the analysis of images captured in the visible and near and far infrared spectrum which involves using non-invasive techniques in order to characterize the growth of a plant and diagnose if it presents any type of stress. This study presents the characterization of vegetative growth and fruiting of jalapeño pepper plants in an aeroponic system, where the root, leaf development parameters and fruits were measured in four jalapeño pepper crops through images of plants captured in the visible (VIS), near infrared (NIR) and far infrared (IR) spectrums. Four crops of thirty jalapeño pepper plants were sown to obtain a total of one hundred and twenty plants which were characterized in the different phases of growth and fruiting. Each of the four jalapeño pepper crops were monitored for sixty days in an aeroponic system in a greenhouse. The first crop was intended to carry out tests to establish the appropriate fertigation times, the next three crops were grown under favorable conditions. Algorithms were developed in Matlab to obtain, over ten image capture sessions, the morphometric and thermal parameters of the roots (perimeter, area, length and average temperature), plants (perimeter, area, height and average temperature), and fruiting. (yield and number of fruits). The statistical analysis was carried out using the ANOVA and Tukey tests considering a value of p ≤ 0.05. The results obtained indicate that there is no significant difference between the characterizations of the four crops. This statement is also supported by the visual analysis of the growth curves parameters of the four crops. In addition, the temperature inside the aeroponic system was contrasted with the ambient temperature and it was verified that the temperature to which the roots are exposed was in the range of 10°C – 20°C. The thermal analysis determined that a plant that presents water stress and is also exposed to high temperatures has an average leaf temperature of 3.7 to 5 °C above the optimal condition for the plant, while a plant with stress at normal temperatures was 1.3 °C higher than the plant without stress.

Objectives: Evaluate hand-held echocardiography (HHE) performed and interpreted by trained Advanced Practice Providers (APPs) on hospitalized CHF patients for image quality and interpretation, by comparing against expert echocardiographer and SE findings. Background: Congestive heart failure (CHF) is associated with increased hospital admissions and mortality. While standard echocardiogram (SE) is the gold standard for cardiac assessment, it is not readily available. Hospitalized CHF patients require rapid assessment for expedited treatment. Methods: Over 6 months, five trained APPs performed HHE on hospitalized CHF patients and interpreted: a) Left ventricular (LV) size, b) LV ejection fraction (LVEF), and c) right atrial pressure (RAP). The study echocardiographer reviewed and blindly interpreted HHE images and compared with APPs and SE findings. Kappa-statistics determined the degree of agreement between APPs and study echocardiographer interpretation of HHE images and SE. Results: 80 CHF patients [age 73±14 years, 58% males; LVEF (by SE) 45±19%; 36.3% body mass indexes ≥30 kg/m2] were enrolled. HHE interpretation by APPs had good agreement for LVEF (kappa 0.79) with study echocardiographer and SE (kappa 0.74), and good agreement for RAP (kappa 0.67) with study echocardiographer. Correlation between absolute LVEF interpretation by study echocardiographer on HHE and SE was r=0.88 (p<0.0001). Conclusions: Trained APPs obtained diagnostic-quality HHE images and interpreted LV function and RAP in CHF patients, with good agreement with the study echocardiographer. LVEF by HHE correlated with LVEF by SE. Our study suggests trained APPs can use HHE to evaluate LVEF and RAP in CHF patients leading to expedited and optimized treatment.

Landward displacement of coastal boulders is a morphodynamic signature of inundation and erosion processes. The study of these movements can provide useful elements for coastal hazards assessment. In this note, using open-access remote sensing resources, the 2017 to 2021 annual mobility of medium, coarse, and very coarse boulders spread over about 100 km of the eastern coast of the Gulf of Taranto (Italy) is detected. A large interannual variability was found. As established by multi-temporal object-based image analysis, one hundred and ten boulders changed position between July 2019 and June 2020, no boulder was displaced between July 2017 and July 2018, and few boulders were displaced between July 2018 and July 2019, and June 2020 and September 2021. A hydrodynamic analysis of the investigated boulder displacement led to the estimation of the energy of nearshore waves that hit the coast. The storm Detlef, that crossed over the Mediterranean Sea during 11-13 November 2019, is presumed to be the main cause of the massive displacement phenomenon.

Estimating Visual Quality of Street Space (VQoSS) is pivotal for urban design, environmental sustainability, civic engagement, etc. Recent advancements, notably in deep learning, have enabled large-scale analysis. However, traditional deep learning approaches are hampered by extensive data annotation requirements and limited adaptability across diverse VQoSS tasks. Multimodal Large Language Models (MLLMs) have recently demonstrated proficiency in various computer vision tasks, positioning them as promising tools for automated VQoSS assessment. In this paper, we pioneer the application of MLLMs to VQoSS change estimation, with our empirical findings affirming their effectiveness. In addition, we introduce Street Quality GPT (SQ-GPT), a model that distills knowledge from the current most powerful but inaccessible (not free) GPT-4, requiring no human efforts. SQ-GPT approaches GPT-4’s performance and is viable for large-scale VQoSS change estimation. In a case study of Nanjin, we showcase the practicality of SQ-GPT and knowledge distillation pipeline. Our work promises to be a valuable asset for future urban studies research.

The integration of artificial intelligence (AI) into medical imaging has guided in an era of transformation in healthcare. This literature review explores the latest innovations and applications of AI in the field, highlighting its profound impact on medical diagnosis and patient care. The innovation segment explores into cutting-edge developments in AI, such as deep learning algorithms, convolutional neural networks, and generative adversarial networks, which have significantly improved the accuracy and efficiency of medical image analysis. These innovations have enabled rapid and accurate detection of abnormalities, from identifying tumors during radiological examinations to detecting early signs of eye disease in retinal images. The article also highlights various applications of AI in medical imaging, including radiology, pathology, cardiology, and more. AI-based diagnostic tools not only speed up the interpretation of complex images but also improve early detection of disease, ultimately delivering better outcomes for patients. Additionally, AI-based image processing facilitates personalized treatment plans, thereby optimizing healthcare delivery. This literature review highlights the paradigm shift that AI has brought to medical imaging, highlighting its role in revolutionizing diagnosis and patient care. By combining cutting-edge AI techniques and their practical applications, it is clear that AI will continue shaping the future of healthcare in profound and positive ways.

The spectrums of one type of object under different conditions have the same features (up, down, protruding, concave) at the same spectral positions, which can be used as primary parameters to evaluate the difference among remotely sensed pixels. Wavelet-feature correlation ratio Markov clustering algorithm (WFCRMCA) for the remotely sensed data is proposed based on an accurate description of abrupt spectral features and an optimized Markov clustering in the wavelet feather space. The peak points can be captured and identified by applying a wavelet transform to spectral data. The correlation ratio between two samples is a statistical calculation of the matched peak point positions on the wavelet feature within an adjustable spectrum domain or a range of wavelet scales. The evenly sampled data can be used to create class centers, depending on the correlation ratio threshold at each Markov step, accelerating the clustering speed by avoiding the computation of Euclidean distance for traditional clustering algorithms, such as K-means and ISODATA. Markov clustering applies several strategies, such as a simulated annealing method and gradually shrinking the clustering size, to control the clustering convergence. At each clustering tempera-ture, it can obtain the best class centers quickly. The experimental results of the Airborne Visible/ Infrared Imaging Spectrometer (AVIRIS) and Thermal Mapping (TM) data have verified its ac-ceptable clustering accuracy and high convergence velocity.

In this paper, a relatively new hyper convolution spectra for characterization liquid, viscoelastic and solid samples is presented. Special attention is paid to the biophysical characterization of epithelial tissues and early detection of cancer of the skin, cervix, colon, and oral cavity. The method is based on the use of two types of white light, diffuse and polarized, from the same LED light sources. Based on the subtraction of the intensity values of these two lights and using the hyper convolution algorithm, the ratio of paired and unpaired electrons of tissue is obtained. This ratio correlates well with the state of the tissue: normal, irritating, precancerous, and cancerous. First, a proof-of-concept studies were performed, and later clinical studies on samples from one thousand two hundred fifteen people were performed. It showed that hyper Opto-Magnetic Imaging Spectroscopy (OMIS) can detect epithelial tissue cancers with an accuracy of 85-96%. Bearing in mind that the OMIS method also acquires the biophysical characteristics of the deeper skin layers (epidermis, basement membrane, dermis) by analysing convolution spectra of RGB channels of both diffuse and polarized white light, it is possible to apply this method in cosmetics (skin hydration, collagen, and elastin states, etc.). During OMIS applications, we noticed places where improvements could be made to increase method’s accuracy using advanced machine learning methodologies.

Descriptive geometry has indispensable applications in many engineering activities, some of which are presented in the first chapter of this paper in order to place the development presented here among them. As a result of the continuous variability of the technological environment according to various optimization aspects, the engineering activities must also be continuously adapted to the changes, which an appropriate approach and formulation are required from the practitioners of descriptive geometry, and can even lead to improvement in the field of descriptive geometry. The imaging procedures are always based on the methods and theorems of descriptive geometry. Resolving contradictions in spatial geometry reconstruction research is a constant challenge, to which a possible answer in many cases is the search for the right projection direction. A special method of enumerating the possible infinite viewpoints for the representation of the surface edge curves is presented in another part of the paper. The procedure for determining the correct directions in a mathematically exact way is also presented through examples. The analysis and some of the results of the Monge mapping, which is suitable for the solution of a mechanical engineering task to be solved in a specific technical environment, are also presented.

Side-scan sonar (SSS) detection is a key method in applications such as underwater environmental security and subsea resource development. The use of acoustic images for seabed target detection has gradually become a mainstream underwater detection method. However, many existing detection approaches primarily concentrate on tracking the evolution path of optical image object detection tasks, resulting in complex structures and limited versatility. To tackle this issue, we introduce a pioneering Dual-Domain Multi-Frequency Network (D2MFNet) meticulously crafted to harness the distinct characteristics of SSS image detection. In D2MFNet, aiming at the underwater detection requirements of small scenes, we introduce a novel method for optimize and improve the detection sensitivity of different frequency ranges and propose a Multi-Frequency Combined Attention Mechanism (MFCAM). This mechanism amplifies the relevance of dual-domain features across different channels and space. Moreover, recognizing that SSS images can provide richer insights after frequency domain conversion, we introduce a Dual-Domain Feature Pyramid Network (D2FPN). By incorporating frequency domain information representation, D2FPN significantly augments the depth and breadth of feature information in underwater small datasets. Our methods are seamlessly designed for integration into existing networks, offering plug-and-play functionality with substantial performance enhancements. We have conducted extensive experiments to validate the efficacy of our proposed techniques, and the results showcase their state-of-the-art performance. MFCAM improves the mAP by 16.9% in the KLSG dataset and 15.5% in the SCTD dataset. The mAP of D2FPN was improved by 8.4% in the KLSG dataset and by 9.8% in the SCTD dataset. We will make our code and models publicly available at https://dagshub.com/estrellaww00/D2MFNet.

Cloud detection in remote sensing images is a crucial preprocessing step that efficiently identifies and extracts cloud-covered areas within the images, ensuring the precision and reliability of subsequent analyses and applications. Given the diversity of clouds and the intricacies of the surface, distinguishing the boundaries between thin clouds and the underlying surface is a major challenge in cloud detection. To address these challenges, an advanced cloud detection method, CloudformerV3, is presented in this paper. The proposed method employs a multi-scale adapter to incorporate dark and bright channel prior information into the model's backbone, enhancing the model's ability to capture prior information and multi-scale details from remote sensing images. Additionally, multi-level large window attention is utilized, enabling high-resolution feature maps and low-resolution feature maps to mutually focus and subsequently merge during the resolution recovery phase. This facilitates the establishment of connections between different levels of feature maps and offers comprehensive contextual information for the model's decoder. Experimental results on the GF1_WHU dataset demonstrate that the method introduced in this paper exhibits superior detection accuracy when compared to state-of-the-art cloud detection models. Furthermore, enhanced detection performance is achieved along cloud edges and with respect to thin clouds, showcasing the efficacy of the proposed method.

Generative AI has gained enormous interest nowadays due to new applications like chatGPT, DALL E, Stable Difussion and Deep Fake. Particularly DALL E, Stable Difussion and others (Adobe Firefly, ImagineArt...) are able to create images from a text prompt and are also able to recreate real photographs. Due to this fact, intense research has arisen to create new image forensics applications able to distinguish between real captured images and videos and artificial ones. Detecting forgeries made with Deep Fake is one of the most researched issues. This paper is about another kind of forgery detection. The purpose of this research aims to detect photo realistic AI created images versus real photos coming from a physical camera. For this purpose, techniques that perform a pixel level feature extraction are used. First one is Photo Response Non-Uniformity (PRNU). PRNU is a special noise due to imperfections on the camera sensor that is used for source camera identification. The underlying idea is that AI images will have a different PRNU pattern. Second one is Error level analysis (ELA). This is other type of feature extraction traditionally used for detecting image editions. In fact, ELA is being used nowadays by photographers to detect manually AI created images. Both kinds of features are used to train Convolutional Neural Networks to differentiate between AI images and real photographs. Good results are obtained achieving accuracy rates over 95%. Both extraction methods are carefully assessed by computing precision/recall and F1-score measurements.

Detecting rotational objects in remote sensing imagery is a significant challenge. These images typically encompass a broad field of view, featuring diverse and intricate backgrounds, with ground objects of various sizes densely scattered. As a result, identifying objects of interest within these images is a daunting task. While the integration of Convolutional Neural Networks (CNN) and Transformer networks leads to some advancements in rotational object detection, there is still room for improvement, particularly in enhancing the extraction and utilization of information related to smaller objects. To address this, our paper presents a multi-scale feature fusion module and a global feature context aggregation module. Initially, we fuse original, shallow, and deep features to reduce the loss of shallow feature information, thereby improving the detection performance of small objects in complex backgrounds. Subsequently, we compute the correlation of contextual information within feature maps to extract valuable insights. We name the newly proposed model the "Multiscale Feature Context Aggregation Module" (MFCA). We evaluate our proposed methodology on three challenging remote sensing datasets: DIOR-R, HRSC, and MAR20. Comprehensive experimental results show that our approach surpasses baseline models by 2.07\% mAP, 1.02\% mAP, and 1.98\% mAP on the DIOR-R, HRSC2016, and MAR20 datasets, respectively.

Global Earth Observation (EO) is becoming increasingly important in understanding and addressing critical aspects of life on our planet about environmental issues, natural disasters, sustainable development and others. EO plays a key role in making informed decisions on applying or reforming land use, responding to disasters, shaping climate adaptation policies etc. EO is also becoming a useful tool for helping professionals make the most profitable decisions, e.g., in real estate or the investment sector. Finding similarities in landscapes may provide useful information regarding applying contiguous policies, taking alike decisions or learning from best practices on events and happenings that have already occurred in similar landscapes in the past. However, current applications of similar landscape retrieval are limited by moderate performance and the need for time-consuming and costly annotations. We propose splitting the similar landscape retrieval task into a set of smaller tasks that aim at identifying individual concepts inherent to satellite images. Our approach relies on several models trained with Unsupervised Representation Learning (URL) on Google Earth images to identify these concepts. We show the efficacy of matching individual concepts for tackling the task of retrieving similar landscape(s) to a user-selected satellite image with a proof-of-concept application of the proposed approach on the geographical territory of the Republic of Cyprus. Our results demonstrate the efficacy of breaking up the landscape similarity task into individual concepts closely related to remote sensing instead of trying to capture all concepts and image semantics with a single model like a single RGB semantics model.

Thermal Non-destructive Testing and Evaluation (NDT&E) is crucial in ensuring the quality and safety of industrial materials, components, and structures. It serves as a key tool for assessing their operational reliability, thus enhancing safety in a wide range of industries. There is a growing demand for dependable, swift, remote, and secure inspection and assessment techniques to detect hidden flaws, especially for sustainable solutions prompts adjustments in design and manufacturing standards. Hidden defects often emerge during the service life of these materials and structures due to various stress factors, potentially resulting in catastrophic failures. This study delves into the optimal and dependable experimental method for conducting fast, remote, and secure inspections and assessments of carbon fiber reinforced polymer materials using Infrared Imaging (IRI) as part of Thermal Non-Destructive Testing and Evaluation (TNDT&E). Additionally, it examines the post-processing approach associated with this technique. This perspective also sheds light on the current state-of-the-art infrared imaging methods employed in TNDT&E, emphasizing their strengths and weaknesses about their ability to detect subsurface defects present within the material Most of the methods discussed in previous research primarily focus on the thermal differences in specific areas of a sample using processed thermal images, even though these images come from analyzing a series of images captured over time. This study highlights the latest research in thermal/infrared non-destructive testing and evaluation, along with the related post-processing techniques. It aims to not only show hidden subsurface defects through thermal differences also provides information about how these defects change over time.

Alzheimer's disease (AD) is a progressive and evolving neurodegenerative disease with an insidious onset that can lead to memory loss and cognitive impairment. There is no effective treatment for this disease. However, early diagnosis plays an important role in treatment planning to slow down its progression, as treatment has the greatest impact in the early stages of the disease. Neurological images obtained through different imaging techniques provide powerful information and help diagnose the disease. With the wide application of deep learning techniques in disease diagnosis, especially the prominence of Convolutional Neural Networks (CNNs) in computer vision and image processing, more and more studies are proposing the use of this algorithm for the diagnosis of AD. In this paper, we first systematically introduce the impact of AD on people, detailing the biomarkers, early clinical symptoms, and risk factors of this disease. Secondly, it goes on to detail the development of CNNs, their form, and methods to help diagnose AD. It is proposed that CNNs can help diagnose AD by analyzing medical imaging data, particularly structural brain scans such as magnetic resonance imaging (MRI) and functional scans such as positron emission tomography (PET). Finally, it is concluded that CNNs are of great importance for the diagnosis of AD and that they are likely to play an increasingly important role in the early detection of the disease, the understanding of disease mechanisms, and ultimately, in the development of effective AD therapies and interventions. CNNs are playing an increasingly important role in the Their potential impact on healthcare emphasizes the importance of continued research and innovation in neural networks and medical imaging.

In recent years, ontology plays an important role in facilitating the semantic description of images which consists of describing the image by a set of words to describe the scene which signifies the belonging of the image. This description specified in several archaeological fields such as cultural, religious objects and heritage objects of France. However, the description of archaeological images is not yet exploited because this field is very diverse. In this article, we present a panel of ontology construction methods as well as archaeological ontologies. Also, we show our own OntunAr ontology to describe Tunisian archaeological images. In addition, we integrate OnTunAr into the automatic annotation of Tunisian archaeological images.

Oral Squamous Cell Carcinoma is one among the most common cancer and early detection is the main key to avoid deaths. Automated diagnostic tools that process the histopathological images of a patient to detect abnormal oral lesions will be very much useful for the clinicians. A deep learning framework have been designed with an intermediate layer between feature extraction layers and classification layers for classifying the histopathological images into two categories, namely normal and oral squamous cell carcinoma. The intermediate layer is constructed using the proposed Swarm Intelligence technique called Modified Gorilla Troops Optimizer. Various optimization algorithms are implemented in literature for optimal parameter identification, weights updating and feature selection in deep learning models, but this work focuses on usage of optimization algorithm as intermediate layer that transforms the extracted features into the features that are more suitable for classification. Three datasets totally comprising 2784 normal and 3632 oral squamous cell carcinoma subjects are considered in this work. Three popular CNN architectures namely InceptionV2, MobileNetV3, and EfficientNetB3 are investigated as feature extraction layers. Two fully connected Neural Network layers along with batch normalization and dropout are used as classification layers. Among the investigated feature extraction models, MobileNetV3 performs well in all the three datasets with the highest accuracy of 0.89. Usage of the proposed Modified Gorilla Troops Optimizer as an intermediate layer boosts this accuracy to 0.95.

Malaria is one of the life-threatening disease caused by the Anopheles mosquitoes affecting the human red blood cells. It is the global health concern which is quite common in tropical as well as sub-tropical parts of the World. Therefore, it is an important to have an effective computer aided system in place for early detection and treatment. State of the art machine learning techniques are used to detect the infected malaria cells from the pool of images. As the visual heterogeneity of the malaria dataset is highly complex and dynamic, therefore higher number of images are needed to train the machine learning models effectively. However, hospitals as well as medical institutions do not share the medical image data for collaboration due to general data protection regulation (GDPR) and data protection act (DPA). To overcome this collaborative challenge, our research is inspired to use the real-time medical image data while using the framework of federated learning (FL) framework that will ensure the data privacy while mutual collaboration of hospitals and medical institutes. We have used the state of the art machine learning models that include the Resnet50 and densenet in a federated learning framework. We have experimented both models in different settings and our preliminary results showed that the densenet model performed better in accuracy (75%) in contrast to resnet50 (72%) while considering 8 clients, while the trend is observed common in 4 clients with the similar accuracy of 94% and 6 client showed that the densenet model performed quite well with the accuracy of 92% while resnet50 achieving only 72%.

Unmanned aerial vehicles (UAV) thermal imagery offers several advantages in environmental monitoring, as it can provide a low-cost, high-resolution, and flexible solution to measure the temperature of the surface of the land. Limitations related to the maximum load of the drone lead to use of lightweight uncooled thermal cameras whose internal components are not stabilized to a constant temperature. Such cameras suffer from several unwanted effects that contribute to the increase in temperature measurement error from ±0.5 °C in laboratory conditions, to ±5 °C in unstable flight conditions. This article describes a post processing procedure, that reduces the above unwanted effects. It consists of following steps: i) devignetting using single image vignette correction algorithm, ii) georeferencing of images using EXIF data, scale-invariant feature transform (SIFT) stitching, and gradient descent optimisation, and iii) temperature calibration by minimisation of bias between overlapping thermal images using gradient descent optimisation. The solution was tested in several case studies of river areas, where natural water bodies were used as a reference temperature benchmark. In all tests, the precision of the measurements was increased. The root of the mean of the Square of Errors RMSE on average was reduced by 39.0% and Mean of the absolute value of Errors MAE by 40.5%. The proposed algorithm can be called self-calibrating, as in contrast to other known solutions is fully automatic, uses only field data and does not require any calibration equipment or additional operator effort. A Python implementation of the solution is available on GitHub.

Deep neural networks (DNNs) have gained prominence in addressing regression problems, offering versatile architectural designs that cater to various applications. In the field of earthquake engineering, seismic response prediction is a critical area of study. Simplified models such as single-degree-of-freedom (SDOF) and multi-degree-of-freedom (MDOF) systems have traditionally provided valuable insights into structural behavior, known for their computational efficiency facilitating faster simulations. However, these models have notable limitations in capturing the nuanced nonlinear behavior of structures and the spatial variability of ground motions. This study focuses on leveraging ambient vibration (AV) measurements of buildings, combined with earthquake (EQ) time-history data, to create a predictive model using a neural network (NN) in image format. The primary objective is to predict a specific building's earthquake response accurately. The training dataset consists of 1,197 MDOF 2D shear models, generating a total of 32,319 training samples. To evaluate the performance of the proposed model, termed MLPER (Machine Learning based Prediction of building structures' Earthquake Response), several metrics are employed. These include mean absolute percentage error (MAPE) and mean deviation angle (MDA) for comparisons in the time domain. Additionally, we assess magnitude-squared coherence values and phase differences (Δφ) for comparisons in the frequency domain. This study underscores the potential of MLPER as a reliable tool for predicting building earthquake response, addressing the limitations of simplified models. By integrating AV measurements and EQ time-history data into a neural network framework, MLPER offers a promising avenue for enhancing our understanding of structural behavior during seismic events, ultimately contributing to improved earthquake resilience in building design and engineering.

Sacroiliac (SI) joint dysfunction can lead to debilitating pain but can be treated with minimally invasive sacroiliac joint fusion (SIJF). This treatment is commonly performed using 2D fluoroscopic guidance. This makes placing the implants without damaging surrounding neural structures challenging. Virtual surgical planning (VSP) using simulated fluoroscopic images may improve perioperative guidance. This article describes a workflow with VSP in SIJF using simulated fluoroscopic images and evaluates achieved implant placement accuracy. Routinely collected survey data on the added value of VSP were also evaluated. Ten interventions were performed on 10 patients by the same surgeon, comprising 30 implants; the median age was 39 years, and all patients were female. The overall mean implant placement accuracy was 4.9 ± 1.26 mm and 4.0 ± 1.44°. There were no malpositioning complications. The VSP helped the surgeon understand the anatomy and determine the optimal position and length of the implants. The average Likert scale score of the survey was 4.7, suggesting a positive role of VSP for SIJF. Planned positions of the implants could be reproduced in surgery with clinically acceptable accuracy and VSP was a valuable asset for the surgeon.

Image registration (IR) is a process that deforms images to align them with respect to a reference space, making it easier for medical practitioners to examine various medical images in a standardized reference frame, such as having the same rotation and scale. This document introduces image registration using a simple numeric example. It provides a definition of image registration along with a space-oriented symbolic representation. This review covers various aspects of image transformations, including affine, deformable, invertible, and bidirectional transformations, as well as medical image registration algorithms such as Voxelmorph, Demons, SyN, Iterative Closest Point, and SynthMorph. It also explores atlas-based registration and multistage image registration techniques, including coarse-fine and pyramid approaches. Furthermore, this survey paper discusses medical image registration taxonomies, datasets, evaluation measures, such as correlation-based metrics, segmentation-based metrics, processing time, and model size. It also explores applications in image-guided surgery, motion tracking, and tumor diagnosis. Finally, the document addresses future research directions, including the further development of transformers.

There has been considerable progress in implicit neural representation to upscale an image to any arbitrary resolution. However, existing methods are based on defining a function to predict the RGB value from just four specific loci. Relying on just four loci is insufficient as it leads to losing fine details from the neighboring region(s). We show that by taking into account the semi-local region leads to an improvement in performance. In this paper, we propose applying a new technique called Overlapping Windows on Semi-Local Region (OW-SLR) to an image to obtain any arbitrary resolution by taking the coordinates of the semi-local region around a point in the latent space. This extracted detail is used to predict the RGB value of a point. We illustrate the technique by applying the algorithm to the Optical Coherence Tomography-Angiography (OCT-A) images and show that it can upscale them to random resolution. This technique outperforms the existing state-of-the-art methods when applied to the OCT500 dataset. OW-SLR provides better results for classifying healthy and diseased retinal images such as diabetic retinopathy and normals from the given set of OCT-A images. The project page is available at https://rishavbb.github.io/ow-slr/index.html

A land cover map of two arctic catchments, nearby the Abisko Scientific Research Station, was obtained from a classification of a Sentinel-2 satellite image and a ground survey performed in July 2022. The two contiguous catchments, Miellajokka and Stordalen, are covered by various ecotypes, from boreal forest to alpine tundra and peatland. Two classification algorithms, support vector machine and random forest, were tested and gave very similar results. The percentage of correctly classified pixels was over 88% in both cases. The developed workflow relies solely on open source software and acquired ground observations. Space organization was directed by the altitude as demonstrated by the intersection of the land cover with the topography. Comparison between this new land cover map and previous ones based on data acquired between 2008 and 2011 shows some trends of vegetation cover evolution in response to climate change in the considered area. This land cover map is key input data for permafrost modeling, and hence for the quantification of climate change impacts in the studied area.

Oriented object detection is a challenging task in scene text detection and remote sensing image analysis, which has attracted extensive attention in recent years with the development of deep learning. Currently, mainstream oriented object detectors are based on preset anchor boxes. This method increases the computational load of the network and cause a large amount of anchor box redundancy. To solve this problem, we propose anchor-free oriented object detection based on the Gaussian centerness(AOGC), a single-stage anchor-free detection method. Our method uses contextual attention FPN(CAFPN) to obtain the contextual information of the target. Then we design a label assignment method for oriented objects. Finally, we develop a Gaussian kernel-based centerness branch, which can effectively determine the significance of different anchors. AOGC achieves mAP of 74.30% on the DOTA-1.0 datasets and 89.80% on the HRSC2016 datasets, respectively. AOGC exhibits superior performance to other methods in oriented anchor-free object detection methods.

Spinal deformity refers to a range of disorders that are defined by anomalous curvature of the spine and may be classified as scoliosis, lordosis, or kyphosis. Among these, scoliosis stands out as the most common type of spinal deformity in human beings, and it can be distinguished by abnormal lateral spine curvature accompanied by axial rotation. Accurate identification of spinal deformity is crucial for a person's diagnosis, and numerous assessment methods have been developed by researchers. Therefore, the present study aims to systematically review recent works on spinal deformity as-assessment for scoliosis diagnosis, utilizing image processing techniques. To gather relevant studies, a search strategy was conducted on three electronic databases (Scopus, ScienceDirect, and PubMed) between 2012 and 2022, using specific keywords and focusing on scoliosis cases. A total of 17 papers fully satisfied the established criteria and were extensively evaluated. Despite variations in methodological designs across the studies, all reviewed articles obtained quality ratings higher than satisfactory. Various diagnostic approaches have been employed, including artificial intelligence mechanisms, image processing, and scoliosis diagnosis systems. These approaches have the potential to save time and, more significantly, can reduce the incidence of human error. While all assessment methods have potential in scoliosis diagnosis, they possess several limitations that can be ameliorated in forthcoming studies. Therefore, the findings of this study may serve as guidelines for the development of a more accurate spinal deformity assessment method that can aid medical personnel in the real diagnosis of scoliosis.

When two black holes form a binary system, each black hole observes an event horizon and a curved distorted space-time region around the other black hole. In this space-time, two such regions are formed, and another black hole forms in the second region from the initial black hole, which may be termed the “image” of the first black hole. The same event occurs for the other black hole also, and an extra image of it is formed. In these conditions, the energy of the system divides between the two black holes and their images. These four new black holes that are formed interact with each other again and produce new horizons and new distorted regions. Each black hole produces an image of all the other black holes and detects the background of six black holes instead of three. Consequently, for four black holes, 24 new black holes arise. The energy of the system will be divided amongst all 24 black holes. This story continues and black holes interact with one another and produce new images. Finally, very light black holes are formed each of which is so weak that it cannot produce strong distortions of space-time. The radiated gravitational waves from these weak black holes could be detected by LIGO as well as the signature of these binary black holes. However, detected waves are only a part of very strong gravitational waves. Each time a part of these waves escapes from the system and reaches the earth, they may be regarded as emitted waves from a new binary black hole. The time between radiated signals decreases, and it may be interpreted that a new supermassive binary black hole is radiating. If radiated signals combine, an explosion of the very strong binary system could be detected.

The primary goal of picture compression is to reduce the amount of unused image data while still storing or transmitting it in a format that is appropriate. The compression of raw binary data is quite different from the compression of a picture, and these differences may be rather substantial. In light of this, compression is often regarded as an essential technique for the purposes of both data storage an d transmission in order to mitigate the excessive amounts of data that are generated by these images. In order to transmit enormous datasets, particularly for the purposes of telemedicine and teleradiology, one needs a significant amount of storage capacity as well as an expansive network. As a result, compression is an important aspect of medical imaging. In addition to the importance of compression, the quality of the photos themselves is also an essential factor in the success of analysis. In addition to this, the amount of time necessary to compress the photographs before sending them should be reduced.

Multi-source image registration often suffered from great radiation and geometric differences. Specifically, gray scale and texture from similar landforms in different source images often show significantly different visual features. And these differences disturb the corresponding point extraction in the following image registration process. Considering that edges between heterogeneous images can provide homogeneous information and more consistent features can be extracted based on image edges, an edge consistency radiation-change insensitive feature transform (EC-RIFT) method is proposed in this paper. Firstly, the noise and texture interference are reduced by preprocessing according to the image characteristics. Secondly, image edges are extracted based on phase congruency, and an orthogonal Log-Gabor filter is performed to replace the global algorithm. Finally, the descriptors are built with logarithmic partition of the feature point neighborhood, which improves the robustness of descriptors. Comparative experiments on datasets containing multi-source remote sensing image pairs show that the proposed EC-RIFT method outperforms other registration methods in terms of precision and effectiveness.

Sea ice extraction and segmentation of remote sensing images is the basis for sea ice monitoring. Machine learning-based image segmentation methods rely on manual sampling and require complex feature extraction. Deep-learning semantic segmentation methods have the advantages of high efficiency, intelligence, and automation. Sea ice segmentation using deep learning methods faces the following problems: in terms of datasets, the high cost of sea ice image label production leads to fewer datasets for sea ice segmentation; in terms of image quality, remote sensing image noise and Severe weather conditions affects image quality, which affects the ac-curacy of sea ice extraction. To address the quantity and quality of the dataset, this study used multiple data augmentation methods for data expansion. To improve the semantic segmentation accuracy, the SC-U2-Net network was constructed using multi-scale inflation convolution and a multi-layer Convolutional Block Attention Module (CBAM) attention mechanism for the U2-Net network. The experiments showed that (1) data augmentation solved the problem of an insuffi-cient number of training samples to a certain extent and improved the accuracy of image seg-mentation. (2) This study designed a multilevel Gaussian noise data augmentation scheme to improve the network's ability to resist noise interference and achieve a more accurate segmenta-tion of images with different degrees of noise pollution. (3) The inclusion of a multi-scale inflation perceptron and multi-layer CBAM attention mechanism improved the ability of U2-Net network feature extraction and enhanced the model accuracy and generalization ability.

Fault detection is an important step for subsurface interpretation and reservoir characterization from 3D seismic images. Due to the numerous and complicated faulting structures of seismic images, manual seismic interpretation is time taking and need intensive work. To overcome this problem, geoscientists are coming up with productive computer-aided techniques for assisting in interpreter science for many years. However, in this paper, we used a pre-trained CNN model to predict faults from the 3D seismic volume of the Poseidon field of Browse Basin, Australia. Basically, this field is highly structured with complex normal faulting throughout the targeted Plover Formations. So, our motivation for this work in this field is to compare machine learning-based fault prediction to user interpreted faults identification with supported by seismic variance attribute. We found very satisfying result using DL with having an improved fault probability volume that outperform variance technology. Therefore, we propose that this workflow could reduce time and able to predict fault quite accurately in any field area.

The aim of this study is to analyse problems related to thermal mapping obtained from thermal data acquired from Unmanned Aerial Systems (UAS) equipped with thermal cameras. We focused on an accurate analysis of uncertainties introduced by the PIX4D Mapper software used to obtain the surface temperature maps of thermal images acquired by the UAS. To achieve this aim, we used artificial thermal reference during the surveys, as well as natural hot targets, i.e. thermal anomalies in the Pisciarelli hydrothermal system in Campi Flegrei caldera (CFc). Artificial thermal targets, expressly created and designed for this goal, are a prototype here called “developed thermal target” (DTT) made by the drone Laboratory at Istituto Nazionale di Geofisica e Vulcanologia - Osservatorio Vesuviano (INGV-OV). We show the results obtained by three surveys during which thermal targets were positioned on land at different flight heights of the UAS. Different heights were also necessary to test spatial resolution of the DTT with the used thermal camera as well as possible temperature differences between the raw images acquired by UAS with the thermal mapping obtained from the PIX4D Mapper software. In this work we have estimated the uncertainty that may be introduced by the mosaic procedure and furthermore we find an attenuation of the measured temperatures introduced by the different distances between the thermal anomaly and sensor. These results appear to be of great importance for the subsequent calibration phase of the thermal maps especially in cases where these methodologies are applied for monitoring purposes of volcanic/geothermal areas.

A land cover map of two arctic catchments, nearby the Abisko Scientific Research Station, was obtained from a classification of a Sentinel-2 satellite image and a ground survey performed in July 2022. The two contiguous catchments, Miellajokka and Stordalen, are covered by various ecotypes, from boreal forest to alpine tundra and peatland. The random forests algorithm correctly identified 88% of polygon pixels reserved for testing. The developed workflow relied solely on open source software and acquired ground observations. Space organization was directed by the altitude as demonstrated by the intersection of the land cover with the topography. Comparison between this new land cover map and previous ones based on data acquired between 2008 and 2011 shows some trends of vegetation cover evolution in response to climate change in the considered area.

Knowledge on the health of banana trees is critical for farmers to profit from banana cultivation. Fusarium wilt and banana blood diseases (BDB), two significant diseases infecting banana trees, are caused by Fusarium oxysporum and Ralstonia syzygii, respectively. They have successfully caused a decline in crop yield as they destroy the trees, starting sequentially from the pseudostem to the fruits. The entire distribution of BDB and Fusarium on a plantation can be understood using advanced geospatial information obtained from multispectral aerial photographs taken using an unmanned aerial vehicle (UAV), combined with the reliable data field of infected trees. Vegetation and soil indices derived from a multispectral aerial photograph, such as normalized difference vegetation index, modified chlorophyll absorption ratio index, normalized difference water index (NDWI) and soil pH, may have to be relied on to explain the precise location of these two diseases. In this study, a random forest algorithm was used to handle a large dataset consisting of two models: the banana diseases multispectral model and the banana diseases spectral model. The results show that the soil indices, soil pH and NDWI are the most important variables for predicting the spatial distribution of these two diseases. Simultaneously, the plantation area affected by BDB is more extensive than that affected by Fusarium, if the variation of planted banana cultivars is not considered.

Due to the special characteristics of the shooting distance and angle of remote sensing satellites, the pixel area ratio of ship targets is small and the feature expression is insufficient, which leads to unsatisfactory ship detection performance and even situations such as missed detection and false detection. In this study, we propose an improved-YOLOv5 algorithm. The improvement strategies mainly include: (1) Add the Convolutional Block Attention Module (CBAM) into the Backbone to enhance the extraction of target-adaptive optimal features; (2) Introduce cross-layer connection channel and lightweight GSConv structure into the Neck to achieve higher-level multi-scale feature fusion and reduce the number of model parameters; (3) The Wise-IoU loss function is used to cal-culate the localization loss in the Output, and assign reasonable gradient gains to cope with dif-ferences in image quality. In addition, during the preprocessing stage of experimental data, a me-dian and bilateral filter method is used for noise reduction to reduce interference from ripples and waves and highlight the information of ship features. The experimental results show that Im-proved-YOLOv5 has a significant improvement in recognition accuracy compared to various mainstream target detection algorithms; Compared to the original YOLOv5s, the mean Average Precision (mAP) has improved by 3.2% and the Frames Per Second (FPN) has accelerated by 8.7%.

This research focused on the perception of visually impaired individuals regarding tactile image creation using 3D printing. We developed and applied an experiment with 28 participants with visual impairments. They performed tasks based on skills whose foundations are needed and used in their daily lives, such as scanning, tactile discrimination, picture and spatial comprehension. The tactile images used in this study were developed by additive manufacturing and printed over 180 g/m² sulphite paper. The best performances were obtained when (1) the tactile image contour line heights were between 0.2 mm and 0.4 mm; and (2) the texture presented densities between 10% and 50%, when alone, or between 10% and 90%, when combined with another texture. The tested line widths (0.8 mm and 1.2 mm) did not present statistically significant differences in the results. Vision status (low vision or blindness) and moment of vision loss (congenital or late blind) did not influence the results. Schooling affected the activities of identifying objects and locating their copies. In the Conclusion section, there is a detailed recommendation list for the production and application of tactile materials, which range from simplifying forms to encouraging the use of both hands during content assimilation.

In recent years, there has been a growing interest in remote sensing image-text cross-modal retrieval due to the rapid development of space information technology and the significant increase in remote sensing image data volume. One approach that has shown promising results in cross-modal retrieval of natural images is the multimodal fusion encoding method. However, remote sensing images have unique characteristics that make the retrieval task challenging. Firstly, the semantic features of remote sensing images are fine-grained, meaning they can be divided into multiple basic units of semantic expression. Additionally, these images exhibit variations in resolution, color, and perspective. Different combinations of basic units of semantic expression can generate diverse text descriptions. These characteristics pose considerable challenges for cross-modal retrieval. To address these challenges, this paper proposes a multi-task guided fusion encoder (MTGFE) based on the multimodal fusion encoding method. The model incorporates three tasks: image-text matching (ITM), masked language modeling (MLM), and the newly introduced multi-view joint representations contrast (MVJRC) task. By jointly training the model with these tasks, we aim to enhance its capability to capture fine-grained correlations between remote sensing images and texts. Specifically, the MVJRC task is designed to improve the model’s consistency in feature expression and fine-grained correlation, particularly for remote sensing images with significant differences in resolution, color, and angle. Furthermore, to address the computational complexity associated with large-scale fusion models and improve retrieval efficiency, this paper proposes a retrieval filtering method. This method achieves higher retrieval efficiency while minimizing accuracy loss. Extensive experiments were conducted on four public datasets to evaluate the proposed method, and the results validate its effectiveness. Overall, this study focuses on remote sensing image-text cross-modal retrieval and introduces the MTGFE model, which combines multimodal fusion encoding with multiple tasks to enhance the model’s ability to capture fine-grained correlations. Additionally, a retrieval filtering method is proposed to improve retrieval efficiency. Experimental results demonstrate the effectiveness of the proposed method.

Digital Twin Cities (DTCs) play a fundamental role in city planning and management. They allow three-dimensional modeling and simulation of cities. 3D semantic segmentation is the foundation for automatically creating enriched DTCs, as well as their updates. Past studies indicate that prior level fusion approaches demonstrate more promising precisions in 3D semantic segmentation compared to point level fusion, features level fusion, and decision level fusion families. In order to improve point cloud enriched semantic segmentation outcomes, this article proposes a new approach for 3D point cloud semantic segmentation through developing and benchmarking three prior level fusion scenarios. A reference approach based on point clouds and aerial images was proposed to compare it with the different developed scenarios. In each scenario, we inject a specific prior knowledge (geometric features,classified images ,etc) and aerial images as attributes of point clouds into the neural network’s learning pipeline. The objective is to find the one that integrates the most significant prior knowledge and enhances neural network knowledge more profoundly, which we have named the "smart fusion approach". The advanced Deep Learning algorithm "RandLaNet" was adopted to implement the different proposed scenarios and the reference approach, due to its excellent performance demonstrated in the literature. The introduction of some significant features associated with the label classes facilitated the learning process and improved the semantic segmentation results that can be achievable with the same neural network alone. Overall, our contribution provides a promising solution for addressing some challenges, in particular more accurate extraction of semantically rich objects from the urban fabric. An assessment of the semantic segmentation results obtained by the different scenarios is performed based on metrics computation and visual investigations. Finally,the smart fusion approach was derived based on the obtained qualitative and quantitative results.

This paper aims at trying to answer the question of whether a low cost drone equipped with a regular camera can serve as a simple device to estimate the size of objects. Ad-ditionally, it assesses if the accuracy of measurement is good enough for using a drone for measurements, relying solely on GPS position and camera. A review of the literature pertaining to ground object measurements was conducted. The availability of such in-struments was evaluated in terms of purchase and rental costs, the number of instru-ments on the market, and the time to obtain them. The most common measurement methods were considered and their unit costs were reviewed. The cost of professional surveying and measuring equipment was compared to the possibility of using low-cost, non-commercial drones to measure objects and surfaces. The quality of the images ob-tained was compared with high-resolution satellite systems. Is an ordinary drone with a standard camera suitable for length measurement without professional measuring equipment? Should the results be considered only in the category of size estimation?

Forensic document examiners can determine the authenticity of questioned documents by analyzing the ink used to create them. If an ink mismatch is found, it could be a sign of scam, backdating, or forgery. In this research a Hyperspectral Images of iVision HHID dataset is used to detect number of possible inks used in document. By using Hyperspectral Images, it’s possible to detect ink mismatch in a given document. In this research unsupervised learning method K-means is used to detect number of inks. Approximate number of clusters are determined by Elbow and Silhouette method before implementation of K-means.

Deep convolutional neural networks (CNN) are favored methods widely used in medical image processing due to their assured shown performance. Recently, the emergence of new lung diseases and the possibility of early detection of their symptoms has attracted many researchers to classify diseases by training deep CNNs on lung CT images. The trained networks are expected to distinguish between lung indications in different diseases, especially at the early stages of them. With the hope of achieving this purpose, we proposed an efficient deep CNN called AFEX-Net with adaptive feature extraction layers that successfully extract distinguishing features and classify chest CT images. The efficiency of the proposed network has two aspects: it is a lightweight network with low number of parameters and fast training and it has adaptive pooling layers and adaptive activation functions to increase its level of compatibility to the input data. The proposed network has been evaluated on a dataset with more than 10K chest CT slices, while an efficient pre-processing method is developed to remove any bias from the images. Additionally, we evaluated the performance of the proposed model on the public COVID-CTset dataset to prove the generalisability of our model. The obtained results confirm the competence of the proposed network in confronting medical images, where prompt and accurate learning is required.

Chenodeoxycholic acid (CA) is a naturally occurring bile acid that is produced in the liver from cholesterol. Three CA complexes using Zn(II), Mg(II), and Ca(II) ions were synthesized to examine the chelation tendencies of CA towards these metal ions. The complexation reaction of CA with the metal ions under investigation was conducted with a 1:1 molar ratio (CA to metal) at 60-70°C in natural media (pH 7-8), which consisted of a binary solvent of MeOH and H2O (1:1). The resulting CA complexes were characterized using analytical data (metal, H, C, and Cl, analysis) and spectral data (UV-visible, FT-IR, and 1H NMR) to elucidate the complexes’ structures. The results suggested that CA in anion form utilized oxygen atoms of the carboxylate group (-COO−) to capture Zn(II), Mg(II), and Ca(II) ions. This produced complexes with the general compositions of [Zn(CA)(H2O)Cl], [Mg(CA)(H2O)Cl]H2O, and [Ca(CA)(H2O)Cl]2H2O, respectively. The Kirby-Bauer disc diffusion assay was then used to explore the bioactivity of the CA complexes toward three fungal species, three Gram-positive bacteria, and two Gram-negative bacteria. The Ca(II) and Mg(II) complexes exhibited marked inhibitory effects on the cell growth of the fungal species Aspergillus niger with potency equal to 127% and 116% of the activity of the positive control, respectively. The Zn(II) and Ca(II) complexes strongly inhibited the growth of Penicillium sp., while the Zn(II) and Mg(II) complexes showed strong growth inhibition towards the Gram-negative species Pseudomonas aeruginosa.

Urban spatial perception critically influences human behavior and emotional reactions, emphasizing the necessity of aligning urban spaces with human needs for enhanced urban living. However, functionality-based categorization of urban architecture is prone to biases, stemming from disparities between objective mapping and subjective perception. These biases can result in urban planning and designs that fail to cater adequately to the needs and preferences of city residents, negatively impacting their quality of life and the city's overall functionality. In this study, we apply machine learning to elucidate these biases within urban spatial perception research, utilizing a three-step methodology: objective mapping, subjective perception analysis, and perception deviation assessment. Our findings reveal that machine learning can expose hidden patterns within this research field, bearing substantial implications for urban planning and design. Of particular note, the study revealed significant discrepancies in the distribution centroids between commercial buildings and residential or public buildings. This result illuminates the spatial organization characteristics of urban architectural functions, serving as a valuable reference for urban planning and development. Moreover, it uncovers the advantages and disadvantages of different data sources and techniques in interpreting urban spatial perception, paving the way for a more comprehensive understanding of the subject. These findings underscore the importance of integrating both objective mapping and subjective perspectives in urban architectural functionality classification.

With the increasing utilization of intelligent mobile devices for online inspection of electrical equipment in smart grids, the limited computing power and storage capacity of these devices pose challenges for deploying large algorithm models and it’s hard to obtain a substantial number of images of electrical equipment in public. In this paper, we propose a novel distillation method that compresses the knowledge of teacher networks into a compact few-shot classification network, employing a global and local knowledge distillation strategy. Central to our method is exploiting the global and local relationship between the features exacted by the backbone of the teacher network and student network. We compare our method with recent state-of-the-art (SOTA) methods on three public datasets and achieve superior performance. Additionally, we contribute a new dataset, namely EEI-100, which is specifically designed for classification of electrical equipment. We validate our method on this dataset and demonstrate its exceptional prediction accuracy of 94.12% when utilizing only 5-shot images.

The prompt and accurate diagnosis of breast lesions, including the distinction between cancer, non-cancer, and suspicious cancer, plays a crucial role in the prognosis of breast cancer. In this paper, we introduce a novel method based on feature extraction and reduction for detection of breast cancer in mammography images. First, we extract features from multiple pre-trained convolutional neural network (CNN) models, and then concatenate them. The most informative features are selected based on their mutual information with the target variable. Subsequently, the selected features can be classified using a machine learning algorithm. We evaluate our approach using four different machine learning algorithms, and our results demonstrate that the neural network-based classifier yields an accuracy as high as 92% for the RSNA dataset which is a new dataset that provides two views and additional features such as age. We compare our proposed algorithm with state-of-the-art methods and demonstrate its superiority, particularly in terms of accuracy and sensitivity. For the MIAS dataset, we achieve an accuracy as high as 94.5%, and for the DDSM dataset, an accuracy of 96% is attained. These results highlight the effectiveness of our method in accurately diagnosing breast lesions and surpassing existing approaches.

Unmanned Aerial Vehicles (UAVs) image object detection has great application value in military and civilian fields. However, the objects in the captured images from UAVs have problems of large scale variation, complex backgrounds, and a large proportion of small objects. To resolve these problems, a multi-scale object detector based on coordinate and global information aggregation is proposed, named CGMDet. Firstly, a Coordinate and Global Information Aggregation Module (CGAM) is designed by aggregating local, coordinate, and global information, which can obtain features with richer context information. Secondly, a Multi-Feature Fusion Pyramid Network (MF-FPN) is proposed, which can better fuse features of different scales and obtain features containing more context information through repeated use of feature maps, to better detect multi-scale targets. Moreover, more location information of low-level feature maps is integrated to improve the detection results of small targets. Furthermore, we modified the bounding box regression loss of the model to make the model more accurately regress the bounding box and faster convergence. Finally, the proposed CGMDet was tested on VisDrone and UAVDT datasets and mAP0.5 of 50.9% and 48% was obtained, respectively. At the same time, our detector achieved the best results compared to other detectors.

Maritime search and rescue is a crucial component of the national emergency response system, which currently mainly relies on Unmanned Aerial Vehicles (UAVs) to detect the objects. Most traditional object detection methods focus on boosting the detection accuracy while neglecting the detection speed of the heavy model. However, it is also essential to improve the detection speed which can provide timely maritime search and rescue. To address the issues, we propose a lightweight object detector named Shuffle-GhostNet-based detector (SG-Det). First, we construct a lightweight backbone, named Shuffle-GhostNet, which enhances the information flow between channel groups by redesigning the correlation group convolution and introducing the channel shuffle operation. Second, we propose an improved feature pyramid model, namely BiFPN-tiny, which has a lighter structure while being capable of reinforcing small object features. Furthermore, we incorporate the atrous spatial pyramid pooling module (ASPP) to the network, which employs atrous convolution with different sampling rates to obtain multi-scale information. Finally, we generate three sets of bounding boxes at different scales – large, medium, and small – to detect objects of different sizes. Compared with other lightweight detectors, SG-Det achieves better tradeoffs across performance metrics, and enables real-time detection with an accuracy rate of over 90% for maritime objects, which shows that it can be better meet the actual requirements of maritime search and rescue.

Panoramic and periapical radiograph tools help dentists diagnose the most common dental diseases. Generally, dentists identify dental caries manually by inspecting X-ray images. However, due to their heavy workload, or poor image quality, dentists may sometimes overlook some unnoticeable dental caries, which may ultimately hinder the patient treatment. The purpose of this study was to develop an algorithm that classifies the teeth X-Ray images into three categories of “Normal”, “Caries”, and “Filled”. Our study used a dataset of 116 patients and 3712 single teeth images for training, validation and testing. Images were pre-processed using a sharpening filter and an intensity color map. We used a pre-trained transfer learning model, the NASNetMobile, which served as the feature extractor and the Convolutional Neural Network (CNN) model served as the classifier. The training dataset had a “Recall” of 0.92, 0.90 and 0.91 for “Normal”, “Caries” and “Filled” respectively and the test dataset had a “Recall” of 0.86, 0.81 and 0.85 for “Normal”, “Caries” and “Filled” respectively. The classification of the teeth X-Rays was successful and can be valuable for dentist as the artificial intelligence algorithm can serve as a decision support tool to aid dentists when they need to diagnose dental treatment.

Convolutional neural networks (CNN) have attracted much attention as a commonly used method for hyperspectral image (HSI) classification in recent years, however, CNNs can only be applied to Euclidean data and have limitations in dealing with relationships due to the limitations of local feature extraction. However, each pixel of a hyperspectral image contains a set of spectral bands that are correlated and interact with each other, and the methods used to process Euclidean data cannot effectively obtain these correlations. In contrast, the graph convolutional network (GCN) can be used in non-Euclidean data, but usually leads to oversmoothing and ignoring local detail features due to the need for superpixel segmentation processing to reduce computational effort. To overcome the above problems, we constructed a network a fusion network based on GCN and CNN, which contains two branches: a graph convolutional network based on superpixel segmentation and a convolutional network with added attention mechanism. The graph convolu-tional branch can extract the structural features and capture the relationships between the nodes, and the convolutional branch can extract the detailed features in the local fine region. Owing to the fact that the features extracted from the two branches are different, the classification performance can be improved by fusing the complementary features extracted from the two branches. To vali-date the proposed algorithm, experiments were conducted on three widely used datasets, namely Indian Pines, Pavia University, and Salinas, and the overall accuracy of 98.78% was obtained in the Indian Pines dataset, and the overall accuracy of 98.99% and 98.69% was obtained in the other two datasets. The results showed that the proposed fusion network can obtain richer features and achieve high classification accuracy.

Fire regimes in mountain landscapes of southern Europe have been shifting from their baselines due to rural abandonment and fire exclusion policies. Understanding the effects of fire on biodiversity is paramount to implement adequate management. Herein, we evaluated the relative role of burn severity and heterogeneity on bird abundance in an abandoned mountain range located in the biogeographic transition between the Eurosiberian and Mediterranean region (the Natural Park ‘Baixa Limia–Serra do Xurés’). We surveyed the bird community in 206 census plots distributed across the Natural Park, both inside and outside areas affected by wildfires over the last 11 years (from 2010 to 2020). We used satellite images of Sentinel 2 and Landsat missions to quantify the burn severity and heterogeneity of each fire within each surveyed plot. We also accounted for the past land use (forestry or agropastoral use) by using a land cover information for year 2010 derived from satellite image classification. We recorded 1,735 contacts from 28 bird species. Our models, fitted by using GLMs with Poisson error distribution (pseudo-R²_-average of 0.22 ± 0.13), showed that up to 71% of the modelled species were linearly correlated with at least one attribute of the fire regime. The spatiotemporal variation in burnt area and severity were relevant factors for explaining the local abundance of our target species (39% of the species; Akaike weights > 0.75). We also found a quadratic effect of at least one fire regime attribute on bird abundance for 60% of the modeled species. The past land use, and its legacy after 10 years, was critical to understand the role of fire (Akaike weights > 0.75). Our findings confirm the importance of incorporating remotely sensed indicators of burn severity into the toolkit of decision makers to accurately anticipate the response of birds to fire management.

The purpose of this work was to achieve non-destructive detection of the internal defects of in-shell walnuts using X-ray radiography technology based on improved Faster R-CNN network model. First, the FPN structure was added to the feature extraction layer to extract richer image information. Then ROI Align was used to instead of ROI Pooling for eliminating the localization bias problem caused by quantization operation. Finally, the Softer-NMS module was introduced to the final regression layer with the predicted bounding box for improving the localization accuracy of the candidate boxes. The results indicated that the internal defects in intact walnuts with shells could be identified effectively using the proposed improved network model in this study. Specifically, the discrimination accuracy of the in-shell sound, shriveled and empty-shell walnuts were 96.14%, 91.72% and 94.80% respectively, and the highest overall accuracy can reach 94.22 %. Contrasted with original Faster R-CNN network model, the mAP and F1-value of the improved Faster R-CNN model increased by 5.86% and 5.65%, respectively. Consequently, the proposed method can be applied for the in-shell walnuts with shriveled and empty-shell defects.

A land cover map of two arctic catchments, nearby the Abisko Scientific Research Station, was obtained from a classification of a Sentinel-2 satellite image and a ground survey performed in July 2022. The two contiguous catchments, Miellajokka and Stordalen, are covered by various ecotypes, from boreal forest to alpine tundra and peatland. The Random Forest algorithm correctly identified 83% of polygon pixels reserved for testing. The developed workflow relied solely on open source software and acquired ground observations. Space organization was directed by the altitude as shown by the intersection of the land cover with the topography. Comparison between this new land cover map and previous ones based on data acquired between 2008 and 2011 demonstrates some trends of vegetation cover evolution in response to climate change in the considered area. The potential applications in terms of permafrost modeling (hiperborea.omp.eu) are finally discussed.

Image fusion is the process of combining multiple input images from single or multiple imaging modalities into a fused image, which is expected to be more informative for human or machine perception as compared to any of the input images. In this paper, we propose a novel method based on deep learning for fusing infrared images and visible images, named the LBP-based proportional input generative adversarial network (LPGAN). In the image fusion task, the preservation of structural similarity and image gradient information is contradictory, and it is difficult for both to achieve good performance at the same time. To solve this problem, we innovatively introduce Local Binary Patterns (LBP) into Generative Adversarial Networks (GANs), which effectively utilize the texture features of the source images, so that the network has stronger feature extraction ability and anti-interference ability. In the feature extraction stage, we introduce a pseudo-siamese network for the generator to extract the detailed features and the contrast features. At the same time, considering the characteristic distribution of different modal images, we propose a 1:4 scale input mode. Extensive experiments on the publicly available TNO dataset and CVC14 dataset show that the proposed method achieves the state-of-the-art performance. We also test the universality of LPGAN through the fusion of RGB and infrared images on the RoadScene dataset. In addition, LPGAN is applied to multi-spectral remote sensing image fusion. Both qualitative and quantitative experiments demonstrate that our LPGAN can not only achieve good structural similarity, but also retain rich detailed information.

Disease control programs need to identify breeding sites of mosquitoes which transmit malaria and other diseases to target interventions and identify environmental risk factors. Increasing availability of very high resolution drone data provides new opportunities to find and characterize these vector breeding sites. Within this study, we identified land cover types associated with malaria vector breeding sites in West Africa. Drone images from two malaria endemic regions in Burkina Faso and Côte d’Ivoire were assembled and labeled using open-source tools. We developed and applied a workflow using region of interest-based and deep learning methods to classify these habitat types from very high resolution natural color imagery. Analysis methods achieved a dice coefficient ranging between 0.68 and 0.88 for different vector habitat types; however, this classifier consistently identified the presence of specific habitat types of interest. This establishes a framework for developing deep learning approaches to identify vector breeding sites and highlights the need to evaluate how results will be used by control programs.

This study aimed to investigate the possibility of using one-shot hyperspectral airborne images to recognize crops for an area with many small plots. The results showed that unsupervised clustering methods could classify crops with an accuracy of 80%, which improved to 90% when restricted to only grain crops, using a single airborne hyperspectral recording. However, additional layers such as NDVI, DTM, slope, and aspect did not improve classification accuracy. For comparison, the accuracy of clustering time series Sentinel-2 images with NDVI layers and DTM-derived data yielded an accuracy of: 74% ,Sentinel-2 time series 68% and single one registration before harvest - 39%. The results of the random forest classification were slightly less accurate due to a lack of sufficient reference data. However, it is challenging to verify the reported accuracy of crop recognition in the literature above 90% due to differences in analysis methodologies, reference data selection, pixel/object approaches, metric choice, and calculation formulas used.

During the pandemic, home-cooked meals have received more attention as people get more time for themselves and their families. It cannot deny that people have more time to prepare meals, and it is safer to cook at home since they can avoid direct contact with people who can potentially F0 or F1. For that particular reason, the number of home cooking has increased rapidly. In the article, the author pointed out that in comparison to the previous time, 42.0 percent of respondents said they cooked more frequently during the lockdown, while just 7.0 percent said they cooked less frequently. The increase in cooking frequency had a more significant impact on women than on men (p<0.05). Those who said they cooked more regularly spent more time preparing meals (78\%) and trying new recipes (73.6\%), as well as spending more time baking (67.1 percent ). In particular, the consumption of “comfort” foods (salty snacks, sweets) showed a significant rise, ranging from (23\%) to (60\%) of respondents who declared snacking more studied.Moreover, articles pointed out that in conjunction with the dramatic reduction in energy expenditure due to the impossibility of going out, this situation could have led to energy imbalance and, thus, weight gain. Noticing the massive rise in home cooking, the search for new recipes, and the need for balance meals, the idea for a cooking app called "Cooking Papa" has been proposed. As far as the research goes, the concept of "cooking" seems close but yet not easy to define. The Oxford English Dictionary defines cooking as “to prepare food by the action of heat. However, limited evidence suggests that people interpret the meaning of cooking quite differently. Moreover, the terms ‘homemade’, ‘convenience,’ ‘proper cooking,’ ‘cook,’ ‘basic ingredients,’ and ‘ready prepared’ are not uniformly understood.

This article proposes application of a new mathematical model of spots for solving inverse problems using a learning method, which is similar to using the deep learning. In general, the spots represent vague figures in abstract “information spaces” or crisp figures with lack of in-formation about their shapes and are adequate for representation human mental images and reasoning in Artificial Intelligence (AI). However, crisp figures are regarded as a special and limiting case of spots. A basic mathematical apparatus, basing on L4 numbers, has been developed for the representation and processing of qualitative information of elementary spatial relations between spots. Also, we defined L4 vectors, L4 matrices, and mathematical operations on them. Developed apparatus can be used in AI, in particular, for knowledge representation and for modeling qualitative reasoning and learning. Another application area is the solution of inverse problems by learning. For example, this can be applied to image reconstruction using ultrasound, X-ray, magnetic resonance, or radar scan data. The introduced apparatus was verified by solving problems of reconstruction of images, utilizing only qualitative data of its elementary relations with some scanning figures. This article also demonstrates application of spot-based inverse Radon algorithm for binary image reconstruction.

Recently, deep learning-based image quality enhancement models have been proposed to improve the perceptual quality of distorted synthesized views impaired by compression and Depth Image Based Rendering (DIBR) process in multiview video systems. However, due to the lack of multi-view video plus depth data, the training data for quality enhancement models is small, which limits the performance and progress of these models. Augmenting the training data to enhance the Synthesized View Quality Enhancement (SVQE) models is a feasible solution. In this paper, we suggest a deep learning-based SVQE model using more synthetic Synthesized View Images (SVIs). To simulate the irregular geometric displacement of DIBR distortion, a random irregular polygon-based SVI synthesis method is proposed based on existing massive RGB/RGBD data, and a synthetic synthesized view database is constructed, which includes synthetic SVIs and DIBR distortion masks. Moreover, to further guide the SVQE models to focus more precisely on DIBR distortion, the DIBR distortion mask prediction network which could predict the position and variance of DIBR distortion is embedded into the SVQE models. The experimental results demonstrate that by pretraining on the synthetic SVI database, the performance of the existing SVQE models could be greatly promoted. In addition, by introducing the DIBR distortion mask prediction network, the SVI quality could be further enhanced.

Although deep learning has received extensive attention and achieved excellent performances in various of scenarios, it suffers from adversarial examples to some extent. Especially, physical attack poses more threats than digital attack. However, existing researches pay less attention to physical attack of object detection in remote sensing images (RSIs). In this work, we systematically analyze the universal adversarial patch attack for multi-scale objects in the remote sensing field. There are two challenges for adversarial attack in RSIs. On one hand, the number of objects in remote sensing images is more than that of natural images. Therefore, it is difficult for adversarial patch to show adversarial effect on all objects when attacking a detector of RSIs. On the other hand, the wide range of height of photography platform causes that the size of objects diverse a lot, which brings challenges for generating universal adversarial perturbation for multi-scale objects. To this end, we propose an adversarial attack method on object detection for remote sensing data. One of the key ideas of the proposed method is the novel optimization of adversarial patch. We aim to attack as many objects as possible by formulating a joint optimization problem. Besides, we raise a scale factor to generate a universal adversarial patch that adapts to multi-scale objects, which ensures the adversarial patch is valid for multi-scale objects in the real world. Extensive experiments demonstrate the superiority of our method against state-of-the-art methods on YOLO-v3 and YOLO-v5. In addition, we also validate the effectiveness of our method in real-world applications.

Vegetation indexes help perform precision farming because they provide useful information regarding moisture, nutrient content, and crop health. Primary sources of those indexes are satellites and unmanned aerial vehicles equipped with expensive multispectral sensors. Reducing the price of obtaining such information would increase the availability of precision farming for small farms. Several studies have proposed deep neural network methods to estimate the indexes from RGB color images. However, these methods report relatively large errors for mature plants when highly non-linear relationships of images and vegetation indexes arise. One could apply multilayer random forest-based models (Deep Forests) to solve this problem, but the discriminative power of such models is limited: they cannot catch complex dependencies between image features. In this paper, we propose a method that combines ideas of deep forests, random forests of kernel trees, and global pruning of random forests to tackle the problem. As a result, the method considers the properties of objects with a complex structure: the presence of relationships between groups of features, displacement, and scaling of objects. The experimental results show that the proposed method outperforms neural network-based solutions in several datasets.

Research has been growing on object detection using semi-supervised methods in past few years. We examine the intersection of these two areas for floor-plan objects to promote the research objective of detecting more accurate objects with less labelled data. The floor-plan objects include different furniture items with multiple types of the same class, and this high inter-class similarity impacts the performance of prior methods. In this paper, we present Mask R-CNN based semi-supervised approach that provides pixel-to-pixel alignment to generate individual annotation masks for each class to mine the inter-class similarity. The semi-supervised approach has a student-teacher network that pulls information from the teacher network and feeds it to the student network. The teacher network uses unlabeled data to form pseudo-boxes, and the student network uses both unlabeled data with the pseudo boxes and labelled data as ground truth for training. It learns representations of furniture items by combining labelled and unlabeled data. On the Mask R-CNN detector with ResNet-101 backbone network, the proposed approach achieves mAP of 98.8%, 99.7%, and 99.8% with only 1%, 5% and 10% labelled data, respectively. Our experiment affirms the efficiency of the proposed approach as it outperforms the fully supervised counterpart using only 10% of the labels.

A problem with synthetic aperture radar (SAR) is that, due to the poor penetrating action of electromagnetic waves inside solid bodies, the capability to observe inside distributed targets is precluded. Under these conditions, imaging action is provided only on the surface of distributed targets. The present work describes an imaging method based on the analysis of micro-movements on the Khnum-Khufu Pyramid, which are usually generated by background seismic waves. The results obtained prove to be very promising, as high-resolution full 3D tomographic imaging of the pyramid's interior and subsurface was achieved. Khnum-Khufu becomes transparent like a crystal when observed in the micro-movement domain. Based on this novelty, we have completely reconstructed internal objects, observing and measuring structures that have never been discovered before. The experimental results are estimated by processing series of SAR images from the second-generation Italian COSMO-SkyMed satellite system, demonstrating the effectiveness of the proposed method.

Segmentation is an important step in medical imaging. In particular, machine learning, especially deep learning, has been widely used to efficiently improve and speed up the segmentation process in clinical practice. Despite the acceptable segmentation results of multi-stage models, little attention was paid to the use of deep learning algorithms for brain image segmentation, which could be due to the lack of training data. Therefore, in this paper, we propose a Generative Adversarial Network (GAN) model that performs transfer learning to segment MRI brain images.Our model enables the generation of more labeled brain images from existing labeled and unlabeled images. Our segmentation targets brain tissue images, including white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). We evaluate the performance of our GAN model using a commonly used evaluation metric, which is Dice Coefficient (DC). Our experimental results reveal that our proposed model significantly improves segmentation results compared to the standard GAN model. We observe that our model is 2.1–10.83 minutes faster than stat-of-the-art-models.

While thunderstorms can pose severe risks to property and life, forecasting remains challenging, even at short lead times, as these often arise in meta-stable atmospheric conditions. In this paper, we examine the question of how well we could perform short-term (up to 180min) forecasts using exclusively multi-spectral satellite images and past lighting events as data. We employ representation learning based on deep convolutional neural networks in an “end-to-end” fashion. Here, a crucial problem is handling the imbalance of the positive and negative classes appropriately in order to be able to obtain predictive results (which is not addressed by many previous machine-learning-based approaches). The resulting network outperforms previous methods based on physically-based features and optical flow methods (similar to operational prediction models) and generalizes across different years. A closer examination of the classifier performance over time and under masking of input data indicates that the learned model actually draws most information from structures in the visible spectrum, with infrared imaging sustaining some classification performance during the night.

Miscanthus holds a great potential in the frame of the bioeconomy and yield prediction can help improving Miscanthus logistic supply chain. Breeding programs in several countries are attempting to produce high-yielding Miscanthus hybrids better adapted to different climates and end-uses. Multispectral images acquired from unmanned aerial vehicles (UAVs) in Italy and in the UK in 2021 and 2022 were used to investigate the feasibility of high-throughput phenotyping (HTP) of novel Miscanthus hybrids for yield prediction and crop traits estimation. An intercalibration procedure was performed using simulated data from the PROSAIL model to link vegetation indices (VIs) derived from two different multispectral sensors. Random forest algorithm estimated with good accuracy yield traits (light interception, plant height, green leaf biomass and standing biomass) using VIs time series and predicted yield using peak descriptor derived from VIs time series with 2.3 Mg DM ha-1 of RMSE. The study demonstrates the potential of UAVs multispectral in HTP applications and in yield prediction for providing important information needed to increase sustainable biomass production.

Remote sensing technology, especially using satellite images, has become essential support in many aspects of decision-making, particularly in disaster risk management. It requires a shorter period of data updates and less cost compared to conventional field observations and surveys. Yet, the intensive processing and high-powered computing resources are necessary to analyze satellite imagery data through Geographic Information System (GIS). In this paper, we introduce the identification and mapping of natural disaster impact in Indonesia using the open-source collaborative tool of Google Earth Engine (GEE) application which analyzes the relative temporal difference of Earth surface from three major satellite images: Sentinel-1, Sentinel-2, and Landsat-8. Taking the advantage of the geographical, geological, and demographic conditions of Indonesia's disaster-prone areas, we analyze relative difference from normalized difference vegetation index (NDVI) out of months before and after natural disaster occurrence to measure the impact of natural disaster in focus study areas. Given the high-vegetation nature of three main natural disaster impacted areas in Indonesia: Aceh, Palu, and Yogyakarta, we are able to simplify the analysis by highlighting areas with vegetative loss or gain after the event. Using an open-source GEE application, namely HazMapper, we identify and visualize the aftermath of the tsunami disaster in Aceh and Palu as well as the earthquake in Yogyakarta. Our study is potentially beneficial for government and decision-makers to utilize publicly available satellite images for disaster recovery and mitigation policy.

At INFN-LNS, and in collaboration with the ATOMKI laboratories, an innovative multi-diagnostic system with advanced analytical methods has been designed and implemented. This is based on several detectors and techniques (Optical Emission Spectroscopy, RF systems, Interfero-polarimetry, X-ray detectors) and here we focus on high resolution spatially-resolved X-ray spectroscopy, performed by means of a X-ray pin-hole camera setup operating in the 0.5−20 keV energy domain. The diagnostic system was installed at a 14 GHz Electron Cyclotron Resonance (ECR) ion source (ATOMKI, Debrecen), enabling high precision X-ray spectrally-resolved imaging of ECR plasmas heated by hundreds of Watts. The achieved spatial and energy resolution were 0.5 mm and 300 eV at 8 keV, respectively. We here present the innovative analysis algorithm that we properly developed for obtaining Single Photon-Counted (SPhC) images providing the local plasma emitted spectrum in a High-Dynamic-Range (HDR) mode, by distinguishing fluorescence lines of the materials of the plasma chamber (Ti, Ta) from plasma (Ar). This method allows a quantitative characterization of warm electrons population in the plasma (and its 2D distribution) which are the most important for ionization, and also to estimate local plasma density and spectral temperatures. The developed post-processing analysis is also able to remove the readout noise, that is often observable at very low exposure times (msec). The setup is now under update including fast shutters and trigger systems in order to allow simultaneously space and time-resolved plasma spectroscopy during transients, stable and turbulent regimes.

Three-dimensional reconstruction plays an important role in assisting doctors and surgeons in diagnosing bone defects’ healing progress. Common three-dimensional reconstruction methods include surface and volume rendering. As the focus is on the shape of the bone, volume rendering is omitted. Many improvements have been made on surface rendering methods like Marching Cubes and Marching Tetrahedra, but not many on working towards real-time or near real-time surface rendering for large medical images, and studying the effects of different parameter settings for the improvements. Hence, in this study, an attempt towards near real-time surface rendering for large medical images is made. Different parameter values are experimented on to study their effect on reconstruction accuracy, reconstruction and rendering time, and the number of vertices and faces. The proposed improvement involving three-dimensional data smoothing with convolution kernel Gaussian size 0.5 and mesh simplification reduction factor of 0.1, is the best parameter value combination for achieving a good balance between high reconstruction accuracy, low total execution time, and a low number of vertices and faces. It has successfully increased the reconstruction accuracy by 0.0235%, decreased the total execution time by 69.81%, and decreased the number of vertices and faces by 86.57% and 86.61% respectively.

Object detection is one of the most critical tasks in the field of Computer vision. This task comprises identifying and localizing an object in the image. Architectural floor plans represent the layout of buildings and apartments. The floor plans consist of walls, windows, stairs, and other furniture objects. While recognizing floor plan objects is straightforward for humans, automatically processing floor plans and recognizing objects is a challenging problem. In this work, we investigate the performance of the recently introduced Cascade Mask R-CNN network to solve object detection in floor plan images. Furthermore, we experimentally establish that deformable convolution works better than conventional convolutions in the proposed framework. Identifying objects in floor plan images is also challenging due to the variety of floor plans and different objects. We faced a problem in training our network because of the lack of publicly available datasets. Currently, available public datasets do not have enough images to train deep neural networks efficiently. We introduce SFPI, a novel synthetic floor plan dataset consisting of 10000 images to address this issue. Our proposed method conveniently surpasses the previous state-of-the-art results on the SESYD dataset and sets impressive baseline results on the proposed SFPI dataset. The dataset can be downloaded from SFPI Dataset Link. We believe that the novel dataset enables the researcher to enhance the research in this domain further.

Macula fovea detection is a crucial prerequisite towards screening and diagnosing macular diseases. Without early detection and proper treatment, any abnormality involving the macula may lead to blindness. However, with the ophthalmologist shortage and time-consuming artificial evaluation, neither accuracy nor effectiveness of the diagnose process could be guaranteed. In this project, we proposed a deep learning approach on ultra-widefield fundus (UWF) images for macula fovea detection. This study collected 2300 ultra-widefield fundus images from Shenzhen Aier Eye Hospital in China. Methods based on U-shape network (Unet) and Fully Convolutional Networks (FCN) are implemented on 1800 (before amplifying process) training fundus images, 400 (before amplifying process) validation images and 100 test images. Three professional ophthalmologists were invited to mark the fovea. A method from the anatomy perspective is investigated. This approach is derived from the spatial relationship between macula fovea and optic disc center in UWF. A set of parameters of this method is set based on the experience of ophthalmologists and verified to be effective. Results are measured by calculating the Euclidean distance between proposed approaches and the accurate grounded standard, which is detected by Ultra-widefield swept-source optical coherence tomograph (UWF-OCT) approach. Through a comparation of proposed methods, we conclude that, deep learning approach of Unet outperformed other methods on macula fovea detection tasks, by which outcomes obtained are comparable to grounded standard method.

Tables in the document image are one of the most important entities since they contain crucial information. Therefore, accurate table detection can significantly improve information extraction from tables. In this work, we present a novel end-to-end trainable pipeline, HybridTabNet, for table detection in scanned document images. Our two-stage table detector uses the ResNeXt-101 backbone for feature extraction and Hybrid Task Cascade (HTC) to localize the tables in scanned document images. Moreover, we replace conventional convolutions with deformable convolutions in the backbone network. This enables our network to detect tables of arbitrary layouts precisely. We evaluate our approach comprehensively on ICDAR-13, ICDAR-17 POD, ICDAR-19, TableBank, Marmot, and UNLV. Apart from the ICDAR-17 POD dataset, our proposed HybridTabNet outperforms earlier state-of-the-art results without depending on pre and post-processing steps. Furthermore, to investigate how the proposed method generalizes unseen data, we conduct an exhaustive leave-one-out-evaluation. In comparison to prior state-of-the-art results, our method reduces the relative error by 27.57% on ICDAR-2019-TrackA-Modern, 42.64% on TableBank (Latex), 41.33% on TableBank (Word), 55.73% on TableBank (Latex + Word), 10% on Marmot, and 9.67% on UNLV dataset. The achieved results reflect the superior performance of the proposed method.

Existing methods enhance mid-low resolution remote sensing ship detection by feeding super-resolved images to the detectors. Although these methods marginally improve the detection accuracy, the correlation between image super-resolution (SR) and ship detection is under-exploited. In this paper, we propose a simple but effective ship detection method called ShipSR-Det, in which both the output image and the intermediate features of the SR module are fed to the detection module. Using the super-resolved feature representation, the potential benefit introduced by image SR can be fully used for ship detection. We apply our method to the SSD and Faster-RCNN detectors and develop ShipSR-SSD and ShipSR-Faster-RCNN, respectively. Extensive ablation studies validate the effectiveness and generality of our method. Moreover, we compare ShipSR-Faster-RCNN with several state-of-the-art ship detection methods. Comparative results on the HRSC2016, DOTA and NWPU VHR-10 datasets demonstrate the superior performance of our proposed method.

Visual Question Generation (VQG) from images is a rising research topic in both fields of natural language processing and computer vision. Although there are some recent efforts towards generating questions from images in the open domain, the VQG task in the medical domain has not been well-studied so far due to the lack of labeled data. In this paper, we introduce a goal-driven VQG approach for radiology images called VQGRaD that generates questions targeting specific image aspects such as modality and abnormality. In particular, we study generating natural language questions based on the visual content of the image and on additional information such as the image caption and the question category. VQGRaD encodes the dense vectors of different inputs into two latent spaces, which allows generating, for a specific question category, relevant questions about the images, with or without their captions. We also explore the impact of domain knowledge incorporation (e.g., medical entities and semantic types) and data augmentation techniques on visual question generation in the medical domain. Experiments performed on the VQA-RAD dataset of clinical visual questions showed that VQGRaD achieves 61.86% BLEU score and outperforms strong baselines. We also performed a blinded human evaluation of the grammaticality, fluency, and relevance of the generated questions. The human evaluation demonstrated the better quality of VQGRaD outputs and showed that incorporating medical entities improves the quality of the generated questions. Using the test data and evaluation process of the ImageCLEF 2020 VQA-Med challenge, we found that relying on the proposed data augmentation technique to generate new training samples by applying different kinds of transformations, can mitigate the lack of data, avoid overfitting, and bring a substantial improvement in medical VQG.

Hyper-spectral images contain a wide range of bands or wavelength due to which they are rich in information. These images are taken by specialized sensors and then investigated through various supervised or unsupervised learning algorithms. Data that is acquired by hyperspectral image contain plenty of information hence it can be used in applications where materials can be analyzed keenly, even the smallest difference can be detected on the basis of spectral signature i.e. remote sensing applications. In order to retrieve information about the concerned area, the image has to be grouped in different segments and can be analyzed conveniently. In this way, only concerned portions of the image can be studied that have relevant information and the rest that do not have any information can be discarded. Image segmentation can be done to assort all pixels in groups. Many methods can be used for this purpose but in this paper, we discussed k means clustering to assort data in AVIRIS cuprite, AVIRIS Muffet and Rosis Pavia in order to calculate the number of regions in each image and retrieved information of 1st, 10th and100th band. Clustering has been done easily and efficiently as k means algorithm is the easiest approach to retrieve information.

For Visually impaired People (VIPs), the ability to convert text to sound can mean a new level of independence or the simple joy of a good book. With significant advances in Optical Character Recognition (OCR) in recent years, a number of reading aids are appearing on the market. These reading aids convert images captured by a camera to text which can then be read aloud. However, all of these reading aids suffer from a key issue – the user must be able to visually target the text and capture an image of sufficient quality for the OCR algorithm to function – no small task for VIPs. In this work, a Sound-Emitting Document Image Quality Assessment metric (SEDIQA) is proposed which allows the user to hear the quality of the text image and automatically captures the best image for OCR accuracy. This work also includes testing of OCR performance against image degradations, to identify the most significant contributors to accuracy reduction. The proposed No-Reference Image Quality Assessor (NR-IQA) is validated alongside established NR-IQAs and this work includes insights into the performance of these NR-IQAs on document images.

Hyperspectral image (HSI) classification is a mechanism of analyzing differentiated land cover in remotely sensed hyperspectral images. In the last two decades, a number of different types of classification algorithms have been proposed for classifying hyperspectral data. These algorithms include supervised as well as unsupervised methods. Each of these algorithms has its own limitations. In this research, three different types of unsupervised classification methods are used to classify different datasets i-e Pavia Center, Pavia University, Cuprite, Moffett Field. The main objective is to assess the performance of all three classifiers K-Means, Spectral Matching, and Abundance Mapping, and observing their applicability on different datasets. This research also includes spectral feature extraction for hyperspectral datasets.

Here, we report the prediction of vegetative stages variables of canary bean crop by means of RGB and multispectral images obtained from UAV during the ripening stage, correlating the vegetation indices with biometric variables measured manually in the field. Results indicated a highly significant correlation of plant height with eight RGB image vegetation indices for the canary bean crop, which were used for predictive models, obtaining a maximum correlation of R2 = 0.79. On the other hand, the estimated indices of multispectral images did not show significant correlations.

In this study, we aimed to develop a deep learning model for identifying bacterial keratitis (BK) and fungal keratitis (FK) by using slit-lamp images. We retrospectively collected slit-lamp images of patients with culture-proven microbial keratitis between January 1, 2010, and December 31, 2019, from two medical centers in Taiwan. We constructed a deep learning algorithm, consisting of a segmentation model for cropping cornea images and a classification model that applies convolutional neural networks to differentiate between FK and BK. The model performance was evaluated and presented as the area under the curve (AUC) of the receiver operating characteristic curves. A gradient-weighted class activation mapping technique was used to plot the heatmap of the model. By using 1330 images from 580 patients, the deep learning algorithm achieved an average diagnostic accuracy of 80.00%. The diagnostic accuracy for BK ranged from 79.59% to 95.91% and that for FK ranged from 26.31% to 63.15%. DenseNet169 showed the best model performance, with an AUC of 0.78 for both BK and FK. The heat maps revealed that the model was able to identify the corneal infiltrations. The model showed better diagnostic accuracy than the previously reported diagnostic performance of both general ophthalmologists and corneal specialists.

Recently, the mapping industry has been focusing on the possibility of large-scale mapping from unmanned aerial vehicles (UAVs) owing to advantages such as easy operation and cost reduction. In order to produce large-scale maps from UAV images, it is important to obtain precise orientation parameters. For this, various techniques have been developed and are included in most of the commercial UAV image processing software. For mapping, it is equally important to select images that can cover a region of interest (ROI) with the fewest possible images. Otherwise, to map the ROI, one may have to handle too many images, and commercial software does not provide information needed to select images, nor does it explicitly explain how to select images for mapping. For these reasons, stereo mapping of UAV images in particular is time consuming and costly. In order to solve these problems, this study proposes a method to select images intelligently. We can select a minimum number of image pairs to cover the ROI with the fewest possible images. We can also select optimal image pairs to cover the ROI with the most accurate stereo pairs. We group images by strips, and generate the initial image pairs. We then apply an intelligent scheme to iteratively select optimal image pairs from the start to the end of an image strip. According to the results of the experiment, the number of images selected is greatly reduced by applying the proposed optimal image–composition algorithm. The selected image pairs produce a dense 3D point cloud over the ROI without any holes. For stereoscopic plotting, the selected image pairs were map the ROI successfully on a digital photogrammetric workstation (DPW), and a digital map covering the ROI is generated. The proposed method should contribute to time and cost reductions in UAV mapping.

In any document, graphical elements like tables, figures, and formulas contain essential information. The processing and interpretation of such information require specialized algorithms. Off-the-shelf OCR components cannot process this information reliably. Therefore, an essential step in document analysis pipelines is to detect these graphical components. It leads to a high-level conceptual understanding of the documents that makes digitization of documents viable. Since the advent of deep learning, the performance of deep learning-based object detection has improved many folds. In this work, we outline and summarize the deep learning approaches for detecting graphical page objects in the document images. Therefore, we discuss the most relevant deep learning-based approaches and state-of-the-art graphical page object detection in document images. This work provides a comprehensive understanding of the current state-of-the-art and related challenges. Furthermore, we discuss leading datasets along with the quantitative evaluation. Moreover, it discusses briefly the promising directions that can be utilized for further improvements.