Deep networks-based hashing has gained significant popularity in recent years, particularly in the field of image retrieval. However, most existing methods only focus on extracting semantic information from the final layer, disregarding valuable structural information that contains important semantic details crucial for effective hash learning. To address this limitation and improve image retrieval accuracy, we propose a novel deep hashing method called Deep Supervised Hashing by Fusing Multiscale Deep Features (DSHFMDF). Our approach involves extracting multiscale features from multiple convolutional layers and fusing them to generate more robust representations for efficient image retrieval. Experimental results on CIFAR10 and NUS-WIDE datasets demonstrate that our method surpasses the performance of state-of-the-art hashing techniques.

Aiming at the problems that are poor generalization performance, low retrieval accuracy and large time consumption of existing content-based image retrieval system, the hierarchical image retrieval method based on multi feature fusion is proposed in this paper. The retrieval accuracy rates on Corel5K, UKbeach and Holidays are 68.23(Top 1), 3.73(N-S) and 88.20(mAp), respectively. The experimental results show that the method proposed in this paper can effectively improve the deficiency of single feature retrieval and save time significantly in the premise of a small amount of loss of accuracy.

Digital images have become an important carrier for people to access information in the information age. However, with the development of the technology, digital images are vulnerable to illegal access and tampering, to the extent that they pose a serious threat to personal privacy, social order and national security. Therefore, image forensic techniques have become an important research topic in the field of multimedia information security. In recent years, deep learning technology has been widely applied in the field of image forensics and the performance achieved has significantly exceeded the conventional forensic algorithms. This survey compares the state-of-the-art image forensic techniques based on deep learning in recent years. The image forensic techniques are divided into passive and active forensics. In passive forensics, forgery detection techniques are reviewed, and the basic framework, evaluation metrics and commonly used datasets for forgery detection are presented. The performance, advantages and disadvantages of existing methods are also compared and analyzed according to different types of detection. In active forensics, robust image watermarking techniques are overviewed, the evaluation metrics and basic framework of robust watermarking techniques are presented. The technical characteristics and performance of existing methods are analyzed based on the different types of attacks on images. Finally, future research directions and conclusions are given to provide useful suggestions for people in image forensics and related research fields.

In the field of computer vision, large-scale image classification tasks are both important and highly challenging. With the ongoing advances in deep learning and optical character recognition (OCR) technologies, neural networks designed to perform large-scale classification play an essential role in facilitating OCR systems. In this study, we developed an automatic OCR system designed to identify up to 13,070 large-scale printed Chinese characters by using deep learning neural networks and fine-tuning techniques. The proposed framework comprises four components, including training dataset synthesis and background simulation, image preprocessing and data augmentation, the process of training the model, and transfer learning. The training data synthesis procedure is composed of a character font generation step and a background simulation process. Three background models are proposed to simulate the factors of the background noise and anti-counterfeiting patterns on ID cards. To expand the diversity of the synthesized training dataset, rotation and zooming data augmentation are applied. A massive dataset comprising more than 19.6 million images was thus created to accommodate the variations in the input images and improve the learning capacity of the CNN model. Subsequently, we modified the GoogLeNet neural architecture by replacing the FC layer with a global average pooling layer to avoid overfitting caused by a massive amount of training data. Consequently, the number of model parameters was reduced. Finally, we employed the transfer learning technique to further refine the CNN model using a small number of real data samples. Experimental results show that the overall recognition performance of the proposed approach is significantly better than that of prior methods and thus demonstrate the effectiveness of proposed framework, which exhibited a recognition accuracy as high as 99.39% on the constructed real ID card dataset.

Diabetic retinopathy (DR), a major complication of prolonged diabetes, poses a significant risk of vision loss. Early detection is critical for effective treatment, yet traditional diagnostic methods by ophthalmologists are time-consuming, costly, and subject to variability. This study introduces a novel approach employing a hybrid Convolutional Neural Network-Radial Basis Function (CNN-RBF) classifier integrated with Multi-Scale Discriminative Robust Local Binary Pattern (MS-DRLBP) features for enhanced DR detection. We implemented advanced image preprocessing techniques, including noise reduction, morphological operations, and Otsu’s thresholding, to optimize blood vessel segmentation from retinal images. Our method demonstrates exceptional performance in screening DR, achieving an average of 96.10% precision, 95.35% sensitivity, 97.06% specificity, and 96.10% accuracy. These results significantly outperform traditional methods and offer a promising tool for remote and efficient screening of DR. Applied to publicly available datasets, this research contributes to the development of accessible, accurate diagnostic methods in ophthalmology, potentially reducing the global burden of diabetic vision loss.

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.

Intracranial hemorrhage is a serious medical problem that requires rapid and often intensive medical care. Identifying the location and type of any hemorrhage present is a critical step in the treatment of the patient. Diagnosis requires an urgent procedure, and the detection of hemorrhage is a difficult and time-consuming process for human experts. In this paper, we propose methods based on EfficientDet’s deep-learning technology that can be applied to the diagnosis of hemorrhages and thus become a decision-support system. Our proposal is two-fold. On the one hand, the proposed technique classifies slices of computed tomography scans for the presence hemorrhage or its lack, achieving 92.7% accuracy and 0.978 ROC-AUC. On the other hand, our methodology provides visual explanations of the classification chosen using the Grad-CAM methodology.

A topic of growing interest in urban remote sensing is the automated extraction of geometrical building information for 3D city modeling. Roof geometry information is useful for applications such as urban planning, solar potential estimation and telecommunication installation planning, and wind flow simulations for pollutant diffusion analysis. Recent research has proven that the advance in remote sensing technologies and deep learning methods offer the prospects of deriving the roof structure information accurately and efficiently. In this study, we propose a Vectorized Roof Extractor- method based on Fully Convolutional Networks (FCNs) and advanced polygonization method to extract roof structure from aerial imagery and a normalized Digital Surface Models (nDSM) in a regularized vector format. The roof structure consists of building outlines, external edges of the building roof, inner rooflines, internal intersections of the main roof planes. The methodology is comprised of segmentation, vectorization and post-processing for outer rooflines, external edges of the building roof, and inner rooflines, and internal intersections of the main roof planes. For the comparison, we adapt the Frame field Learning (FFL) method originally designed to extract building polygons [1]. Our experiments are conducted on a custom data set derived for the city of Enschede, The Netherlands, using aerial imagery, nDSM and manually digitized training polygons. The results show that the proposed Vectorized Roof Extractor outperformed adapted FFL on PoLiS distance with values of 3.5 m and 1.2 m for outlines and inner rooflines, respectively. Furthermore, the model surpassed the adapted FFL on PoLiS-thresholded F-score for outlines and inner rooflines, with 0.31 and 0.57, respectively. The Vectorized Roof Extractor produced adequate visual results, with straighter walls and fewer missed inner roofline detections. It can predict buildings with common walls thanks to skeleton graph computation. To summarize, the proposed method is suitable for urban applications and has the potential to be improved further.

An effective on-board cloud detection method in small satellites would greatly improve the downlink data transmission efficiency and reduce the memory cost. In this paper, an ensemble method combining a lightweight U-Net with wavelet image compression is proposed and evaluated. The red, green, blue and infrared waveband images from Landsat-8 dataset are trained and tested to estimate the performance of proposed method. The LeGall-5/3 wavelet transform is applied on the dataset to accelerate the neural network and improve the feasibility of on-board implement. The experiment results illustrate that the overall accuracy of the proposed model achieves 97.45% by utilizing only four bands. Tests on low coefficients of compressed dataset have shown that the overall accuracy of the proposed method is still higher than 95%, while its inference speed is accelerated to 0.055 second per million pixels and maximum memory cost reduces to 2Mb. By taking advantage of mature image compression system in small satellites, the proposed method provides a good possibility of on-board cloud detection based on deep learning.

Deep Learning is a recent and important addition to the computational toolbox available for image reconstruction in fluorescence microscopy. We review state-of-the-art applications such as image restoration, super-resolution, and light-field imaging, and discuss how the latest Deep Learning research can be applied to other image reconstruction tasks such as structured illumination, spectral deconvolution, and sample stabilisation. Despite its successes, Deep Learning also poses significant challenges, has often misunderstood capabilities, and overlooked limits. We will address key questions, such as: What are the challenges in obtaining training data? Can we discover structures not present in the training data? And, what is the danger of inferring unsubstantiated image details?

Medical brain image analysis is a necessary step in the Computers Assisted /Aided Diagnosis (CAD) systems. Advancements in both hardware and software in the past few years have led to improved segmentation and classification of various diseases. In the present work, we review the published literature on systems and algorithms that allow for classification, identification, and detection of White Matter Hyperintensities (WMHs) of brain MRI images specifically in cases of ischemic stroke and demyelinating diseases. For the selection criteria, we used the bibliometric networks. Out of a total of 140 documents we selected 38 articles that deal with the main objectives of this study. Based on the analysis and discussion of the revised documents, there is constant growth in the research and proposal of new models of deep learning to achieve the highest accuracy and reliability of the segmentation of ischemic and demyelinating lesions. Models with indicators (Dice Score, DSC: 0.99) were found, however with little practical application due to the uses of small datasets and lack of reproducibility. Therefore, the main conclusion is to establish multidisciplinary research groups to overcome the gap between CAD developments and their complete utilization in the clinical environment.

Breast cancer is a common malignant tumour and studies have shown that early and accurate detection is crucial for patients. With the maturity of medical imaging and deep learning development, significant progress has been made in breast cancer classification, which greatly improves the accuracy and efficiency of classification. This review focuses on deep learning, migration learning, GAN, and lifelong learning to elaborate and summarise the important roles arising from breast cancer detection. This review also examines the dataset and labeling issues required for breast cancer classification. In conclusion, at the end of the article, we look at future directions for breast cancer classification research, including cross-migration learning, multimodal data fusion, model interpretability, and lifelong learning, and also explore how to provide personalized treatment plans for patients.

In modern security situations, tracking multiple human objects in real-time within challenging urban environments is a critical capability for enhancing situational awareness, minimizing response time, and increasing overall operational effectiveness. Tracking multiple entities enables informed decision-making, risk mitigation, and the safeguarding of civil-military operations to ensure safety and mission success. This paper presents a multi-modal electro-optical/infrared (EO/IR) and radio frequency (RF) fused sensing (MEIRFS) platform for real-time human object detection, recognition, classification, and tracking in challenging environments. By utilizing different sensors in a complementary manner, the robustness of the sensing system is enhanced, enabling reliable detection and recognition results across various situations. Specifically designed Radar tag and thermal tag can be used to discriminate friendly and non-friendly objects. The system incorporates deep learning-based image fusion and human object recognition and tracking (HORT) algorithms to ensure accurate situation assessment. After integrating into an all-terrain robot, multiple ground tests were conducted to verify the consistent HORT in various environments. The MEIRFS sensor system has been designed to meet the Size, Weight, Power, and Cost (SWaP-C) requirements for installation on autonomous ground and aerial vehicles.

Single Image Super Resolution (SSIR) is a problem in computer vision where the goal is 1 to create high-resolution images from low-resolution ones. It has important applications in fields 2 such as medical imaging and security surveillance. While traditional methods such as interpolation 3 and reconstruction-based models have been used in the past, deep learning techniques have recently 4 gained attention due to their superior performance and computational efficiency. This article proposes 5 an Autoencoder based Deep Learning Model for SSIR, in particular, a light model that uses fewer 6 parameters without compromising performance. The down-sampling part of the Autoencoder 7 mainly uses 3 by 3 convolution and has no subsampling layers. The up-sampling part uses transpose 8 convolution and residual connections from the down sampling part. The model is trained using a 9 subset of the VILRC ImageNet database. The model is evaluated using quantitative metrics PSNR, 10 SSIM as well as qualitative measures such as perceptual quality. PSNR and SSIM figures as high as 11 76.06 and 0.93 are reported.

Computer vision is a powerful technology that has enabled solutions in various fields by analyzing visual attributes in images. One field that has taken advantage of computer vision is agricultural automation, which promotes high-quality crop production. The nutritional status of a crop is a crucial factor in determining its productivity. This status is mediated by approximately 14 chemical elements acquired by the plant, and their determination plays a pivotal role in farm management. To address the timely identification of nutritional disorders, this study focuses on the classification of three levels of phosphorus deficiencies through individual leaf analysis. The methodological steps include: (1) generating a database with laboratory-grown maize plants that were induced to total phosphorus deficiency, medium deficiency, and total nutrition, using different capture devices; (2) processing the images with state-of-the-art transfer learning architectures (i.e. VGG16, ResNet50, GoogLeNet, DenseNet201, and MobileNetV2); and (3) evaluating the classification performance of the models using the created database. The results show that the VGG16 model achieves superior performance, with 98% classification accuracy. However, the other studied architectures also demonstrate competitive performance and are considered state-of-the-art automatic leaf deficiency detection tools. The proposed method can be a starting point to fine-tune machine vision-based solutions tailored for real-time monitoring of crop nutritional status.

Deep learning heavily relies on statistical correlations to drive artificial intelligence (AI) innovations, particularly in computer vision applications like autonomous driving and robotics. However, despite providing a solid foundation for deep learning, these statistical correlations can be vulnerable to unforeseen and uncontrolled factors. The lack of prior knowledge guidance can result in spurious correlations, introducing confounding factors and affecting the model's robustness. To address this challenge, recent research efforts have focused on integrating causal theory into deep learning methodologies. By modelling the inherent and unbiased causal structure, causal theory can potentially mitigate the impact of spurious correlations effectively. Hence, this paper explores the basics of causal methodologies in image classification.

Pig farms management is involved in multiple factors such as environmental conditions, animal behavior, weight gaining and others. In all those scenarios, it is fundamental to detect each individual and its development as it grows to reach the shipment phase. Therefore, the objective of this study was to apply an automatic individual pig detection algorithm using Deep Learning Techniques, in frames taken from videos recorded during the weaning phase in real production conditions of small and medium producers in tropical conditions in Colombia. The weaning phase was selected because individual detection in each cage is more difficult due to environmental adaptations that piglets undergo after nursing. Piglets tend to cluster together during this phase, making image processing more challenging compared to the fattening phase, where animals are more isolated. The You Only Look Once (YOLOv7) algorithm and VGG Image Annotator were used to detect individuals in two pens separated by gender. All animal postures, lighting conditions were considered. The Precision, Recall and mAP metrics were used to assess the model performance with different confidence values. A precision of 98.3% in a threshold of 0.9 was reached, Recall of 98.5% in a threshold of 0.85. Data augmentation techniques were important to increase the dataset and to have a more realistic model for individuals’ detection. The method used allowed us to identify all the complete pigs’ bodies under different posture and lighting situations.

Diseases of cereals caused by pathogenic fungi can significantly reduce crop yields. Many cultures are exposed to them. The disease is difficult to control on a large scale, thus one of the relevant approaches is the crop field monitoring, which helps to identify the disease at an early stage and take measures to prevent its spread. One of the effective control methods is disease identification based on the analysis of digital images with the possibility of obtaining them in field conditions using mobile devices. In this work, we propose a method for the recognition of five fungal diseases of wheat shoots (leaf rust, stem rust, yellow rust, powdery mildew, and septoria), both separately and in combination, with the possibility of identifying the stage of plant development. A set of 2414 images of wheat fungi diseases (WFD2020) was generated, for which expert labeling was performed by the type of disease. WFD2020 data are available freely at http://wfd.sysbio.ru/. In the process of creating this set, a method was applied to reduce the degeneracy of the training data based on the image hashing algorithm. The disease recognition algorithm is based on the convolutional neural network with the EfficientNet architecture. The best accuracy (0.942) was shown by a network with a training strategy based on augmentation and transfer of image styles. The recognition method was implemented by the authors as a bot on the Telegram platform, which allows assessing plants by lesions in the field conditions.

Olive fruits at different ripening stages give rise to various table olive products and oil qualities. Therefore, developing an efficient method for recognizing and sorting olive fruits based on their ripening stages can greatly facilitate postharvest processing. This study introduces an automatic computer vision system that utilizes deep learning technology to classify the `Roghani` Iranian olive cultivar into five ripening stages using color images. The developed model employs convolutional neural networks (CNN) and transfer learning based on the Xception architecture and ImageNet weights as the base network. The model was fine-tuned by testing multiple configurations of well-known CNN layers. To minimize overfitting and enhance model generality, data augmentation techniques were employed. By considering different optimizers and two image sizes, four final candidate models were generated. These models were then compared in terms of loss and accuracy on the test dataset, classification performance (classification report and confusion matrix), and generality. All four candidates exhibited high accuracies ranging from 86.93% to 93.46% and comparable classification performance. In all models, at least one class was recognized with 100% accuracy. However, by taking into account the risk of overfitting, two models were discarded. Finally, a model with an image size of 224 × 224 and an SGD optimizer, which had a loss of 1.23 and an accuracy of 86.93%, was selected as the preferred option. The results of this study offer robust tools for automatic olive sorting systems, simplifying the differentiation of olives at various ripening levels for different post-harvest products.

Vision loss can be avoided if diabetic retinopathy (DR) is diagnosed and treated promptly. Following are the main 5 DR stages: none, moderate, mild, proliferate, and severe. In this study, a deep learning (DL) model is presented that diagnoses all 5 stages of DR with more accuracy than previous methods. The suggested method presents two scenarios: case 1 with image enhancement using contrast limited adaptive histogram equalization (CLAHE) filtering algorithm in conjunction with an Enhanced Super-resolution generative adversarial network (ESRGAN), and case 2 without image enhancement; augmentation techniques are then performed to generate a balanced dataset utilizing the same parameters for both cases. Using Inception-V3 applied to the Asia Pacific Tele-Ophthalmology Society (APTOS) datasets, the developed model achieved an accuracy of 98.7% for case 1 and 80.87% for case 2, which is greater than existing methods for detecting the five stages of DR. It was demonstrated that using CLAHE and ESRGAN improves a model's performance and learning ability.

Mineral identification is an important part of geological analysis. Traditional identification methods rely on either the experiences of the appraisers or the various measuring instruments and the methods are either easily influenced by the experiences or need too much work. To solve the above problems, there have been studies using image recognition and intelligent algorithms to identify minerals. But the current studies can not identify many minerals, and the accuracy is low. To increase the number of identified mineral categories and the accuracy, we proposed the method that uses both the mineral images and the Mohs hardness in the deep neural networks to identify the minerals. The experimental results showed that the method can reach 94.0% Top-1 accuracy and 99.9% Top-5 accuracy for 28 common minerals. The model that combines image and Mohs hardness together can identify more minerals and increase the accuracy using less training data.

Alzheimer’s disease has become a major concern in the healthcare domain as it is growing rapidly. Many researches have been conducted to detect it from MRI images through various deep-learning approaches. However, the problem of the availability of medical data and the privacy of the patients still exists. To mitigate this issue in Alzheimer’s disease detection, we have implemented the federated approach which is found to be more efficient, robust, and consistent compared to the conventional approach. For this, we needed deep excavation on various orientations of MRI images and transfer learning architectures. Then, we utilized the publicly available two datasets (OASIS, and ADNI), and designed various cases to evaluate the performance of the federated approach. In almost all of them, the federated approach achieved better accuracy and sensitivity. In distinguishing between two classes equally, the capability of the models was better in the found model when trained with federated approach compared to the conventional approach. In this approach. MobileNet, which is a low-cost transfer learning architecture, achieved the highest 95.24%, 81.94%, and 83.97% accuracy in OASIS, ADNI, and merged (ADNI+OASIS) test set, which was way higher than the achieved performance in Conventional approach. Moreover, in this approach, only the weights of the model were shared which keeps the original MRI images in their respective hospital or institutions, mitigating the privacy concern in the healthcare domain.

The classification of vessel types in SAR imagery is of crucial importance for maritime applications. However, the ability to use real SAR imagery for deep learning classification is limited, due to the general lack of such data and/or the labor-intensive nature of labeling them. Simulating SAR images can overcome these limitations, allowing the generation of an infinite number of datasets. In this contribution, we present a synthetic SAR imagery dataset with ship wakes, which comprises 46080 images for ten different real vessel models. The variety of simulation parameters includes 16 ship heading directions, 6 ship velocities, 8 wind directions, 2 wind velocities, and 3 incidence angles. In addition, we extensively investigate classification performance for noise-free, noisy, and denoised ship wake scenes. We utilize the standard AlexNet architecture and employ training from scratch. To achieve the best classification performance, we conduct Bayesian optimization to determine hyperparameters. Results demonstrate that the classification of vessel types based on their SAR signatures is highly efficient, with maximum accuracies of 96.16%, 92.7%, and 93.59%, when training using noise-free, noisy, and denoised datasets respectively. Thus, we conclude that the best strategy in practical applications should be to train convolutional neural networks on denoised SAR datasets. The results show that the versatility of the SAR simulator can open up new horizons in the application of machine learning to a variety of SAR platforms.

Modern hyperspectral imaging technologies generate enormous datasets that could potentially transmit a wealth of information, but such a resource presents numerous difficulties for data analysis and interpretation. Deep learning techniques undoubtedly provide a wide range of potential for solving both traditional imaging tasks and exciting new problems in the spatial-spectral domain. This is true in the primary application area of remote sensing, where hyperspectral technology originated and has made the majority of its progress, but it may be even more true in the vast array of now existing and developing application areas that make use of these imaging technologies. The current review advances on two fronts: on the one hand, it is directed at domain experts who desire an updated overview of how deep learning architectures might work in conjunction with hyperspectral acquisition techniques to address specific tasks in various application sectors. On the other hand, by providing them with a picture of how deep learning technologies are applied to hyperspectral data from (near)real-time perspective. The contributions of this review include the existence of these two points of view and the inclusion of opportunities and important problems associated with the development of future CHIME mission to be launched by European Space Agency (ESA).

As the Autonomous Vehicle (AV) industry is rapidly advancing, classification of non-motorized (vulnerable) road users (VRUs) becomes essential to ensure their safety and to smooth operation of road applications. The typical practice of non-motorized road users’ classification usually takes numerous training time and ignores the temporal evolution and behavior of the signal. In this research effort, we attempt to detect VRUs with high accuracy be proposing a novel framework that includes using Deep Transfer Learning, which saves training time and cost, to classify images constructed from Recurrence Quantification Analysis (RQA) that reflect the temporal dynamics and behavior of the signal. Recurrence Plots (RPs) were constructed from low-power smartphone sensors without using GPS data. The resulted RPs were used as inputs for different pre-trained Convolutional Neural Network (CNN) classifiers including constructing 227×227 images to be used for AlexNet and SqueezeNet; and constructing 224×224 images to be used for VGG16 and VGG19. Results show that the classification accuracy of Convolutional Neural Network Transfer Learning (CNN-TL) reaches 98.70%, 98.62%, 98.71%, and 98.71% for AlexNet, SqueezeNet, VGG16, and VGG19, respectively. The results of the proposed framework outperform other results in the literature (to the best of our knowledge) and show that using CNN-TL is promising for VRUs classification. Because of its relative straightforwardness, ability to be generalized and transferred, and potential high accuracy, we anticipate that this framework might be able to solve various problems related to signal classification.

In recent years, weeds is responsible for most of the agricultural yield losses. To deal with this threat, farmers resort to spraying pesticides throughout the field. Such method not only requires huge quantities of herbicides but impact environment and humans health. One way to reduce the cost and environmental impact is to allocate the right doses of herbicide at the right place and at the right time (Precision Agriculture). Nowadays, Unmanned Aerial Vehicle (UAV) is becoming an interesting acquisition system for weeds localization and management due to its ability to obtain the images of the entire agricultural field with a very high spatial resolution and at low cost. Despite the important advances in UAV acquisition systems, automatic weeds detection remains a challenging problem because of its strong similarity with the crops. Recently Deep Learning approach has shown impressive results in different complex classification problem. However, this approach needs a certain amount of training data but, creating large agricultural datasets with pixel-level annotations by expert is an extremely time consuming task. In this paper, we propose a novel fully automatic learning method using Convolutional Neuronal Networks (CNNs) with unsupervised training dataset collection for weeds detection from UAV images. The proposed method consists in three main phases. First we automatically detect the crop lines and using them to identify the interline weeds. In the second phase, interline weeds are used to constitute the training dataset. Finally, we performed CNNs on this dataset to build a model able to detect the crop and weeds in the images. The results obtained are comparable to the traditional supervised training data labeling. The accuracy gaps are 1.5% in the spinach field and 6% in the bean field.

Several studies suggest that COVID-19 may be accompanied by symptoms such as a dry cough, muscle aches, sore throat, and mild to moderate respiratory illness. The symptoms of this disease indicate the fact that COVID-19 causes noticeable negative effects on the lungs. Therefore, considering the health status of the lungs using X-rays and CT scans of the chest can significantly help diagnose COVID-19 infection. Due to the fact that most of the methods that have been proposed to COVID-19 diagnose deal with the lengthy testing time and also might give more false positive and false negative results, this paper aims to review and implement artificial intelligence (AI) image-based diagnosis methods in order to detect coronavirus infection with zero or near to zero false positives and false negatives rates. Besides the already existing AI image-based medical diagnosis method for the other well-known disease, this study aims on finding the most accurate COVID-19 detection method among AI methods such as machine learning (ML) and artificial neural network (ANN), ensemble learning (EL) methods.

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.

Semantic image segmentation has recently witnessed considerable progress by training deep convolutional neural networks (CNNs). The core issue of this technique is the limited capacity of CNNs to depict visual objects. Existing approaches tend to utilize approximate inference in a discrete domain or additional aides and do not have a global optimum guarantee. We propose the use of the multi-label manifold ranking (MR) method in solving the linear objective energy function in a continuous domain to delineate visual objects and solve these problems. We present a novel embedded single stream optimization method based on the manifold ranking (MR) model to avoid approximations without sacrificing expressive power. In addition, we propose a novel network, which we refer to as dual multi-scale manifold ranking (\textbf{DMSMR}) network, that combines the dilated, multi-scale strategies with the single stream MR optimization method in the deep learning architecture to further improve the performance. Experiments on high resolution images, including close-range and remote sensing datasets, demonstrate that the proposed approach can achieve competitive accuracy without additional aides in an end-to-end manner.

Diabetic retinopathy (DR) is the primary factor leading to vision impairment and blindness in diabetic people. Uncontrolled diabetes can damage the retinal blood vessels. Initial detection and prompt medical intervention are vital in preventing progressive vision impairment. Today's growing medical field poses more significant workload and diagnostic demands on medical professionals. In the proposed study, a convolutional neural network (CNN) is employed to detect the stages of DR. This research is crucial for studying DR because of its innovative methodology incorporating two different public datasets. This strategy enhances the model's capacity to generalize unseen DR images, as each dataset encompasses unique demographics and clinical circumstances. The network can learn and capture complicated hierarchical image features with asymmetric weights. Each image undergoes preprocessing using contrast-limited adaptive histogram equalization (CLAHE) and the discrete wavelet transform (DWT). The model is trained and validated using the combined datasets of Dataset for Diabetic Retinopathy (DDR) and the Asia Pacific Tele-Ophthalmology Society (APTOS). The CNN model is tuned with different learning rates and optimizers. The CNN model with Adam optimizer achieved 70% accuracy and an area under curve (AUC) score of 0.82. The recommended study results may reduce diabetes-related vision impairment by early DR severity identification.

Pattern recognition techniques form the heart of most, if not all, incoherent linear shift-invariant systems. When an object is recorded using a camera, the object information gets sampled by the point spread function (PSF) of the system, replacing every object point with the PSF in the sensor. The PSF is a sharp Kronecker Delta-like function when the numerical aperture (NA) is large with no aberrations. When the NA is small, and the system has aberrations, the PSF appears blurred. In the above case, if the PSF is known, then the object information can be obtained by scanning the PSF over the recorded object intensity pattern and looking for pattern matching conditions through a mathematical process called correlation. In this study, a recently developed deconvolution method, the Lucy-Richardson-Rosen algorithm (LR2A), has been implemented to computationally refocus images recorded in the presence of spatio-spectral aberrations. The performance of LR2A was compared against the Lucy-Richardson algorithm and non-linear reconstruction. LR2A exhibits a superior deconvolution capability even in extreme cases of spatio-spectral aberrations and blur. Experimental results of deblurring a picture captured using high-resolution smartphone cameras are presented. LR2A was implemented to significantly improve the performances of the widely used deep convolutional neural networks for image classification.

One of the most important challenges in the Machine and Deep Learning areas today is to build good models using small datasets, because sometimes it is not possible to have large ones. Several techniques have been proposed in the literature to address this challenge. This paper aims at studying the different available Deep Learning techniques and performing a thorough experimentation to analyze which technique or combination thereof improves the performance and effectiveness of the models. A complete comparison with classical Machine Learning techniques was carried out, to contrast the results obtained using both techniques when working with small datasets. Thirteen algorithms were implemented and trained using three different small datasets (MNIST, Fashion MNIST, and CIFAR-10). Each experiment was evaluated using a well-established set of metrics (Accuracy, Precision, Recall, F1, and the Matthews correlation coefficient). The experimentation allowed concluding that it is possible to find a technique or combination of them to mitigate a lack of data, but this depends on the nature of the dataset, the amount of data, and the metrics used to evaluate them.

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.

Skin cancer is one of the widespread diseases that typically develop on the skin due to continuous exposure to sunlight. Although cancer can appear on any part of the human body, skin cancer reports account for over half of all cancer occurrences worldwide. There are substantial obstacles to the precise diagnosis and classification of skin lesions because of the morphological variety and indistinguishable characteristics across skin malignancies. Recently, Deep Learning models have been used in the field of image-based lesion diagnosis, and it has demonstrated diagnostic efficiency on par with that of dermatologists. To increase classification efficiency and accuracy for skin lesions, a cutting-edge multi-layer deep Convolutional Neural Network (CNN) termed SkinLesNet has been built in this study. The ResNetV50 and VGG16 models have been carefully compared to review the performance of the proposed model. The dataset used in this study, PAD-UFES-20, contains 1314 samples in total and includes three common forms of skin lesions. The proposed approach, SkinLesNet, significantly outperforms the well-known compared models in the given conditions

Interest in drone solutions in forestry applications is growing. Using drones, datasets can be captured flexibly and at high spatial and temporal resolutions when needed. In forestry applications, fundamental tasks include the detection of individual trees, tree species classification, bio-mass estimation, etc. Deep Neural Networks (DNN) have shown superior results when comparing with conventional machine learning methods such as Multi-Layer Perceptron (MLP) in cases of huge input data. The objective of this research was to investigate 3D convolutional neural networks (3D-CNN) to classify three major tree species in a boreal forest: pine, spruce, and birch. The proposed 3D-CNN models were employed to classify tree species in a test site in Finland. The classifiers were trained with a dataset of 3039 manually labelled trees. Then the accuracies were assessed by employing independent datasets of 803 records. To find the most efficient set of feature combination, we compare the performances of 3D-CNN models trained with hyperspectral (HS) channels, RGB channels, and canopy height model (CHM), separately and combined. It is demonstrated that the proposed 3D-CNN model with RGB and HS layers produces the highest classification accuracy. The producer accuracy of the best 3D-CNN classifier on the test dataset were 99.6%, 94.8%, and 97.4% for pines, spruces, and birches, respectively. The best 3D-CNN classifier produced ~5% better classification accuracy than the MLP with all layers. Our results suggest that the proposed method provides excellent classification results with acceptable performance metrics for HS datasets. Our results show that pine class was detectable in most layers. Spruce was most detectable in RGB data, while birch was most detectable in the HS layers. Furthermore, the RGB datasets provide acceptable results for many low-accuracy applications.

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.

Forest fire identification is important for forest resource protection. Effective monitoring of forest fires requires the deployment of multiple monitors with different viewpoints, while most traditional recognition models can only recognize images from a single source. By ignoring the information from images with different viewpoints, these models produce high rates of missed and false alarms. In this paper, we propose a graph neural network model based on the similarity of dynamic features of multi-view images to improve the accuracy of forest fire recognition. The input features of the nodes on the graph are converted into relational features of different gallery pairs by establishing pairs (nodes) representing different viewpoint images and gallery images. The new feature library relationship is used to update the image gallery with dynamic features in order to achieve the estimation of similarity between images and improve the image recognition rate of the model. In addition, to reduce the complexity of image pre-processing process and extract key features in images effectively, this paper also proposes a dynamic feature extraction method for fire regions based on image segment ability. By setting the threshold value of HSV color space, the fire region is segmented from the image, and the dynamic features of successive frames of the fire region are extracted. The experimental results show that, compared with the baseline method Resnet, this paper's method is more effective in identifying forest fires, and its recognition accuracy is improved by 2%. And the scheme of this paper can adapt to different forest fire scenes, with better generalization ability and anti-interference ability.

Accurate cloud quantification is essential in climate change research. In this work, we construct an automated computer vision framework by synergistically incorporating deep neural networks and finite sector clustering to achieve robust whole sky image-based cloud classification, adaptive segmentation, and recognition under intricate illumination dynamics. A bespoke YOLOv8 architecture attains over 95% categorical precision across four archetypal cloud varieties curated from extensive annual observations (2020) at a Tibetan highland station. Tailor-made segmentation strategies adapted to distinct cloud configurations, allied with illumination-invariant image enhancement algorithms, effectively eliminate solar interference and substantially boost quantitative performance even in illumination-adverse analysis scenarios. Compared with the traditional threshold analysis method, the cloud quantification accuracy calculated within the framework of this paper is significantly improved. Collectively, the methodological innovations provide an advanced solution to markedly escalate cloud quantification precision levels imperative for climate change research, while offering a paradigm for cloud analytics transferable to various meteorological stations.

Urinary cytology is a useful, essential diagnostic method in routine urological clinical practice. Liquid-based cytology (LBC) for urothelial carcinoma screening is commonly used in the routine clinical cytodiagnosis because of its high cell collection rate. Since conventional screening processes by cytoscreeners and cytopathologists using microscopes is limited in terms of human resources, it is important to integrate new deep learning methods that can automatically and rapidly diagnose a large amount of specimens without delay. The goal of this study was to investigate the use of deep learning models for the classification of urine LBC whole-slide images (WSIs) into neoplastic and non-neoplastic (negative). We trained deep learning models using 786 WSIs by transfer learning, fully supervised, and weakly supervised learning approaches. We evaluated the trained models on two test sets (equal and clinical balance) with a combined total of 750 WSIs, achieving ROC-AUCs for WSI diagnosis in the range of 0.984-0.990 by the best model, demonstrating the promising potential use of our model for aiding urine cytodiagnostic processes.

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.

Chest X-ray (CXR) is the first tool globally employed to detect cardiopulmonary pathologies. These acquisitions are highly affected by scattered photons due to the large field-of-view required. Scatter in CXRs introduces background in the images, which reduces their contrast. We developed three deep learning-based models to estimate and correct the scatter contribution to CXRs. We used a Monte Carlo (MC) ray-tracing model to simulate CXRs from human models obtained from CT scans using different configurations (depending on the availability of dual-energy acquisitions). The simulated CXRs contained the separated contribution of direct and scattered X-rays in the detector. These simulated datasets were then used as the reference for the supervised training of several NN. Three NN models (single and dual energy) were trained with the MultiResUNet architecture. The performance of the NN models was evaluated on CXRs obtained with the MC code from chest CTs of patients affected by COVID-19. The results showed that the NN models were able to estimate and correct the scatter contribution to CXRs with an error <5%, being robust to variations in the simulation setup and improving the contrast in soft tissue. The single-energy model was tested with real CXRs, providing robust estimations of the scatter-corrected CXRs.

Near Earth Asteroids represent potential threats to human life because their trajectories may bring them in the proximity of the Earth. Monitoring these objects could help predict future impact events, but such efforts are hindered by the large numbers of objects that pass through the Earth’s vicinity. Additionally, there is also the problem of distinguishing asteroids from other objects in the night sky, which implies sifting through large sets of telescope image data. Within this context, we believe that employing machine learning techniques could greatly improve the detection process by sorting out the most likely asteroid candidates to be reviewed by human experts. At the moment, the use of machine learning techniques is still limited in the field of astronomy and the main goal of the present paper is to study the effectiveness of deep CNNs for the classification of astronomical objects, asteroids in this particular case, by comparing some of the well-known deep convolutional neural networks, including InceptionV3, Xception, InceptionResNetV2 and ResNet152V2. We have applied transfer learning and fine-tuning on these pre-existing deep convolutional networks and from the results that we have obtained one can see the potential of using deep convolutional neural networks in the process of asteroid classification. The InceptionV3 model has the best results in the asteroid class, meaning that by using it, we loose the least number of valid asteroids.

In recent years, demand has been increasing for target detection and tracking from aerial imagery via drones using onboard powered sensors and devices. We propose a very effective method for this application based on a deep learning framework. A state-of-art embedded hardware system empowers small flying robots to carry out the real-time onboard computation necessary for object tracking. Two types of embedded modules were developed: one is designed using a Jetson TX or AGX Xavier, and the other is based on an Intel Neural Compute Stick. These are suitable for real-time onboard computing power on small flying drones with limited space. A comparative analysis of current state-of-art deep-learning-based multi-object detection algorithms was carried out utilizing the designated GPU-based embedded computing modules to obtain detailed metric data about frame rates as well as the computation power. We also introduce an effective target tracking approach for moving objects. The algorithm for tracking moving objects is based on the extension of simple online and real-time tracking. It was developed by integrating a deep-learning-based association metric approach (Deep SORT), which uses a hypothesis tracking methodology with Kalman filtering and a deep-learning-based association metric. In addition, a guidance system that tracks the target position using a GPU-based algorithm is introduced. Finally, we demonstrate the effectiveness of the proposed algorithms by real-time experiments with a small multi-rotor drone.

Over recent years, the importance of patent literature has become more recognized in the academic setting. In the context of artificial intelligence, deep learning, and data sciences, patents are relevant to not only industry but also academe and other communities. In this article, we focus on deep tomographic imaging and perform a preliminary landscape analysis of the related patent literature. Our search tool is PatSeer . Our patent bibliometric data is summarized in various figures and tables. In particular, we qualitatively analyze key deep tomographic patent literature.

Vertical Indoor Farming (VIF) with hydroponics offers a promising perspective for sustainable food production. Intelligent control of VIF system components plays a key role in reducing operating costs and increasing crop yields. Modern machine vision (MV) systems use Deep Learning (DL) in combination with camera systems for various tasks in agriculture, such as disease and nutrient deficiency detection, and flower and fruit identification and classification for pollination and harvesting. This study presents the applicability of MV technology with DL modelling to detect the growth stages of chilli plants using YOLOv8 networks. The influence of different bird’s eye and side view datasets and different YOLOv8 architectures was analysed. To generate the image data for training and testing the YOLO models, chilli plants were grown in a hydroponic environment and imaged throughout their life cycle using four camera systems. The growth stages were divided into growing, flowering and fruiting classes. All trained YOLOv8 models showed reliable identification of growth stages with high accuracy. The results indicate that models trained with data from both views show better generalisation. YOLO’s middle architecture achieved the best performance.

This paper describes a proposed fractional filter-based multi-scale underwater and hazy image enhancement algorithm. The proposed system combines a modified global contrast operator with fractional order-based multi-scale filters used to generate several images, which are fused based on entropy and standard deviation. The multi-scale-global enhancement technique enables fully adaptive and controlled colour correction and contrast enhancement without over exposure of highlights when processing hazy and underwater images. This in addition to illumination/reflectance estimation coupled with global and local contrast enhancement. The proposed algorithm is also compared with the most recent available state-of-the-art multi-scale fusion de-hazing algorithm. Experimental comparisons indicate that the proposed approach yields better edge and contrast enhancement results without halo effect, colour degradation and is faster and more adaptive than all other algorithms from the literature.

It is crucial to select the right machine learning classifier for image classification and face recog-nition. This study examines the effectiveness of four different face recognition classifiers - Support Vector Machines (SVM), Random Forest, K-Nearest Neighbors (KNN), and Neural Networks. An analysis of the Large Faces in the Wild (LFW) dataset was carried out using Principal Component Analysis (PCA). Classifiers are rigorously trained and evaluated based on the extracted features. Comparison of classifier performance is an insightful way to figure out their strengths and weaknesses. Having a visual representation of the classifier's performance gives a complete understanding of its capabilities. Through the selection of the most appropriate classifier, study results contribute to advancements in image classification, recognition, and biometric identification. The comparison study demonstrated that the Neural Network classifier was exceptionally accurate and proficient in recognizing faces from the LFW dataset when used in conjunction with PCA for feature extraction. According to the comparative analysis, the Neural Network classifier proved exceptionally accurate and proficient at identifying faces from the LFW dataset when combined with PCA for feature extraction.

In recent years, data providers are generating and streaming a large number of images. More particularly, processing images that contain faces have received great attention due to its numerous applications, such as entertainment and social media apps. The enormous amount of images shared on these applications presents serious challenges and requires massive computing resources to ensure efficient data processing. However, images are subject to a wide range of distortions in real application scenarios during the processing, transmission, sharing, or combination of many factors. So, there is a need to guarantee acceptable delivery content, even though some distorted images do not have access to their original version. In this paper, we present a framework developed to estimate the images' quality while processing a large number of images in real-time. Our quality evaluation is measured using an integration of a deep network with random forests. In addition, a face alignment metric is used to assess the facial features. Experimental results have been conducted on two artificially distorted benchmark datasets, LIVE and TID2013. We show that our proposed approach outperforms the state-of-art methods, having a Pearson Correlation Coefficient (PCC) and Spearman Rank Order Correlation Correlation Coefficient (SROCC) with subjective human scores of almost 0.942 and 0.931 while minimizing the processing time from 4.8ms to 1.8ms.

Retinopathy is a human eye disease that causes changes in retinal blood vessels that leads to bleed, leak fluid and vision impairment. Symptoms of retinopathy are blurred vision, changes in color perception, red spots, and eye pain. In this paper, a new methodology based on Convolutional Neural Networks (CNN) is developed and proposed to diagnose and give a decision about the presence of retinopathy. The CNN model is trained by different images of eyes that have retinopathy and those which do not have retinopathy. The performance of the proposed model is compared with the related methods of DREAM, KNN, GD-CNN and SVM. Experimental results show that the proposed CNN performs better.

To ensure the security of highly sensitive remote sensing images (RSI) during their transmission, it is essential to implement effective content security protection methods. Generally, secure distribution schemes for remote sensing images often employ cryptographic techniques. However, sending encrypted data exposes communication behavior, which poses significant security risks to the distribution of remote sensing images. Therefore, this paper introduces deep information hiding to achieve secure distribution of remote sensing images, which can serve as an effective alternative in certain specific scenarios. Specifically, the Deep Information Hiding for RSI Distribution (hereinafter referred to as DIH4RSID) based on encoder-decoder network architecture with Parallel Attention Mechanisms (PAM) by adversarial training was proposed. Our model is constructed with four main components: a preprocessing network (PN), an embedding network (EN), a revealing network (RN) and a discriminating network (DN). The PN module is primarily based on Inception to capture more details of RSI and targets of different scales. The PAM module obtains features in two spatial directions to realize feature enhancement and context information integration. The experimental results indicate that our proposed algorithm achieves relatively higher visual quality and secure level compared to related methods. Additionally, after extracting the concealed content from hidden images, the average classification accuracy is unaffected.

Although neural network architectures are critical for their performance, how the structural characteristics of a neural network affect its performance has still not been fully explored. We here map architectures of neural network to directed acyclic graphs, and find that incoherence, a structural characteristic to measure the order of directed acyclic graphs, is a good indicator for the performance of corresponding neural networks. Therefore we propose a deep isotropic neural network architecture by folding a chain of same blocks then connecting the blocks with skip connections at different distances. Our models, named FoldNet, have two distinguishing features compared with traditional residual neural netowrks. First, the distances between block pairs connected by skip connections increase from always equal to one to specially selected different values, which lead to more incoherent graphs and let the neural network explore larger receptive fields and thus enhance its multi-scale representation ability. Second, the number of direct paths increases from one to multiple, which leads to a larger proportion of shorter paths and thus improve the direct propagation of information throughout the entire network. Image classification results on CIFAR-10 and Tiny ImageNet benchmarks suggested that our new network architecture performs better than traditional residual neural networks.

In recent years, the analysis of macro- and micro-expression has drawn the attention of researchers since they provide visual cues of an individual's emotions for a broad range of potential applications such as lie detection and criminal detection. In this paper, we address the challenge of spotting facial macro- and micro-expression from videos and present compelling results by using a deep learning approach to analyze the optical flow features. Different from other deep learning approaches that are mainly based on Convolutional Neural Networks (CNNs), we propose a Transformer-based deep learning approach that predicts a score indicating the probability of a frame being within an expression interval. In contrast to other Transformer-based models that achieve high performance by being pre-trained on large datasets, our deep learning model, called SL-Swin, which incorporates Shifted Patch Tokenization and Locality Self-Attention into the backbone network Swin Transformer, effectively spots macro- and micro-expressions by being trained from scratch on small-size expression datasets. Our evaluation outcomes surpass the MEGC 2022 spotting baseline result, obtaining an overall F1-score of 0.1366. Additionally, our approach also performs well in the MEGC 2021 spotting task with an overall F1-score of 0.1824 and 0.1357 on CAS(ME)^2 and SAMM Long Videos, respectively. The code is publicly available on GitHub (https://github.com/eddiehe99/pytorch-expression-spotting).

Few-shot fine-grained image classification (FSFGIC) methods refer to machine learning methods which aim to classify images (e.g., bird species, flowers, and airplanes) belonging to subordinate object categories of the same entry-level category with only a few samples. It is worth to note that feature representation learning is used not only to represent training samples, but also to construct classifiers for performing various FSFGIC tasks. In this paper, starting from the definition of FSFGIC, a taxonomy of feature representation learning for FSFGIC is proposed. According to this taxonomy, we discuss key issues on FSFGIC (including data augmentation, local or/and global deep feature representation learning, class representation learning, and task specific feature representation learning). The existing popular datasets and evaluation standards are introduced. Furthermore, a novel classification performance evaluation mechanism is designed with a 0.95 confidence interval for judging whether the classification accuracy obtained by a certain specified method is good or bad. Moreover, current challenges and future trends of feature representation learning on FSFGIC are elaborated.

To support pathologists in breast tumor diagnosis, deep learning plays a crucial role in the development of histological whole slide image (WSI) classification methods. However, automatic classification is challenging due to the high-resolution data and the scarcity of representative training data. To tackle these limitations, we propose a deep learning-based breast tumor gigapixel histological image multi-classifier integrated with a high-resolution data augmentation model to process the entire slide by exploring its local and global information and generating its different synthetic versions. The key idea is to perform classification and augmentation in feature latent space, reducing the computational cost while preserving the class label of the input. We adopt a deep learning-based multi-classification method and evaluate the contribution given by a Conditional Generative Adversarial Network-based data augmentation model on the classifier’s performance for three tumor classes in the BRIGHT Challenge dataset. The proposed method has allowed us to achieve an average F1 equal to 69.5, considering only the WSI dataset of the Challenge. The results are comparable to those obtained by the Challenge winning method (71.6), also trained on the annotated tumor region dataset of the Challenge.

COVID-19 is a severe global problem, and AI can play a significant role in preventing losses by monitoring and detecting infected persons in early-stage. This paper aims to propose a high-speed and accurate fully-automated method to detect COVID-19 from the patient's CT scan images. We introduce a new dataset that contains 48260 CT scan images from 282 normal persons and 15589 images from 95 patients with COVID-19 infections. At the first stage, this system runs our proposed image processing algorithm to discard those CT images that inside the lung is not properly visible in them. This action helps to reduce the processing time and false detections. At the next stage, we introduce a novel method for increasing the classification accuracy of convolutional networks. We implemented our method using the ResNet50V2 network and a modified feature pyramid network alongside our designed architecture for classifying the selected CT images into COVID-19 or normal with higher accuracy than other models. After running these two phases, the system determines the condition of the patient using a selected threshold. We are the first to evaluate our system in two different ways. In the single image classification stage, our model achieved 98.49% accuracy on more than 7996 test images. At the patient identification phase, the system correctly identified almost 234 of 245 patients with high speed. We also investigate the classified images with the Grad-CAM algorithm to indicate the area of infections in images and evaluate our model classification correctness.

Target detection and segmentation in synthetic aperture radar (SAR) images are vital steps for many remote sensing applications. In the era of data-driven deep learning, this task is extremely challenging due to the limited labeled data. Few-shot Learning has the ability to learn quickly from few samples with supervised information. Inspired by this, a few-shot learning framework named MSG-FN is proposed to solve the segmentation of ship targets in heterologous SAR images with few annotated samples. The proposed MSG-FN adopts a dual-branch network consisting of a support branch and a query branch. The support branch is used to extract features with an encoder, and the query branch uses a U-shaped encoder-decoder structure to segment the target in the query image. The encoder of each branch is composed of well-designed residual blocks combined with filter response normalization to capture robust and domain-independent features. A multi-scale similarity guidance module is proposed to improve the scale adaptability of detection by applying hand-on-hand guidance of support features to query features of various scales. In addition, a SAR dataset named SARShip-4i is built to evaluate the proposed MSG-FN and the experimental results show that the proposed method achieves superior segmentation results compared with the state-of-the-arts.

Drone and aerial remote sensing images are widely used, but their imaging environment is complex and prone to image blurring. Existing CNN deblurring algorithms usually use multi-scale fusion to extract features in order to make full use of aerial remote sensing blurred image information, but images with different degrees of blurring use the same weights, leading to increasing errors in the feature fusion process layer by layer. Based on the physical properties of image blurring, this paper proposes an adaptive multi-scale fusion blind deblurred generative adversarial network (AMD-GAN), which innovatively applies the degree of image blurring to guide the adjustment of the weights of multi-scale fusion, effectively suppressing the errors in the multi-scale fusion process and enhancing the interpretability of the feature layer. The research work in this paper reveals the necessity and effectiveness of a priori information on image blurring levels in image deblurring tasks. By studying and exploring the image blurring levels, the network model focuses more on the basic physical features of image blurring. Meanwhile, this paper proposes an image blurring degree description model, which can effectively represent the blurring degree of aerial remote sensing images. The comparison experiments show that the algorithm in this paper can effectively recover images with different degrees of blur, obtain high-quality images with clear texture details, outperform the comparison algorithm in both qualitative and quantitative evaluation, and can effectively improve the object detection performance of aerial remote sensing blurred images. Moreover, the average PSNR of this paper's algorithm tested on the publicly available dataset RealBlur-R reached 41.02dB, surpassing the latest SOTA algorithm.

Deep neural networks have been extensively researched in the field of document image classification to improve classification performance and have shown excellent results. However, there is little research in this area that addresses the question of how well these models would perform in a real-world environment, where the data the models are confronted with often exhibits various types of noise or distortion. In this work, we present two separate benchmark datasets, namely RVL-CDIP-D and Tobacco3482-D, to evaluate the robustness of existing state-of-the-art document image classifiers to different types of data distortions that are commonly encountered in the real world. The proposed benchmarks are generated by inserting 21 different types of data distortions with varying severity levels into the well-known document datasets RVL-CDIP and Tobacco3482, respectively, which are then used to quantitatively evaluate the impact of the different distortion types on the performance of latest document image classifiers. In doing so, we show that while the higher accuracy models also exhibit relatively higher robustness, they still severely underperform on some specific distortions, with their classification accuracies dropping from ~90% to as low as ~40% in some cases. We also show that some of these high accuracy models perform even worse than the baseline AlexNet model in the presence of distortions, with the relative decline in their accuracy sometimes reaching as high as 300-450% that of AlexNet. The proposed robustness benchmarks are made available to the community and may aid future research in this area.

Deep convolutional neural network (CNN) has shown their great advantages in the single image deraining task. However, most existing CNN-based single image deraining methods still suffer from residual rain streaks and details lost. In this paper, we propose a deep neural network including the Multi-scale feature extraction module and the channel attention module, which are embed in the feature extraction sub-network and the rain removal sub-network respectively. In the feature extraction sub-network, the Multi-scale feature extraction module is constructed by a Multi-layer Laplacian pyramid, and is then integrated multi-scale feature maps by a feature fusion module. In the rain removal sub-network, the channel attention module, which assigns different weights to the different channels, is introduced for preserving image details. Experimental results on visually and quantitatively comparison demonstrate that the proposed method performs favorably against other state-of-the-art approaches

The agricultural sector in Palestine has a significant role in its economy. However, the production of this sector is affected by different kinds of plant diseases, specifically leaf diseases. Automatic agricultural leaf disease detection is essential for the early diagnosis and controls the overall health of fields. Image segmentation techniques, clustering, and deep learning are often used to detect diseased leaves. This study proposes a novel hybrid approach based on image classification. The hybrid approach combines the k-means clustering algorithm with Convolutional Neural Network (CNN), where k-means is used to detect the leaf’s infected area, then CNN is used for specifying the disease. We used the PlantVillage dataset for experimental verification as it contains several crops with different kinds of challenging diseases. We also examined the selection of optimal k-value using the Silhouette coefficient, Elbow method, and Kneedle Algorithm. The Silhouette technique was analyzed using three distance metrics; Euclidean, Manhattan, and Cosine. Its scores for the three-distance metrics were low, near-zero, and failed to produce the optimum k value. Besides, the Elbow method was complicated to use in image segmentation in terms of executing and visualizing the k value in its graph plot. Based on verification results, the Kneedle Algorithm produced better results in the consistency of choosing the optimal k value and showed superiority over other approaches. Therefore, the processed images were segmented with the k-means clustering algorithm with a Kneedle algorithm-based k value. Finally, a Convolutional Neural Network (CNN) is trained to classify the type of disease based on analyzing and testing leaf images. The hybrid model achieved high accuracy of 93.79% in disease identification, confirming the proposed model’s robustness.

Abstract: Image aesthetic assessment (IAA) with neural attention has made significant progress due to its effectiveness in object recognition. Current studies have shown that the features learned by convolutional neural networks (CNN) at different learning stages indicate meaningful information. The shallow feature contains the low-level information of images and the deep feature perceives the image semantics and themes. Inspired by this, we propose a visual enhancement network with feature fusion (FF-VEN). It consists of two sub-modules, the visual enhancement module (VE module) and the shallow and deep feature fusion module (SDFF module). The former uses an adaptive filter in the spatial domain to simulate human eyes according to the region of interest (ROI) extracted by neural feedback. The latter not only takes out the shallow feature and the deep feature by transverse connection, but also uses a feature fusion unit (FFU) to fuse the pooled features together with the aim of information contribution maximization. Experiments on standard AVA dataset and Photo.net dataset show the effectiveness of FF-VEN.

The analysis of microscopy images has always been an important yet time consuming process in in materials science. Convolutional Neural Networks (CNNs) have been very successfully used for a number of tasks, such as image segmentation. However, training a CNN requires a large amount of hand annotated data, which can be a problem for material science data. We present a procedure to generate synthetic data based on ad-hoc parametric data modelling for enhancing generalization of trained neural network models. Especially for situations where it is not possible to gather a lot of data, such an approach is beneficial and may enable to train a neural network reasonably. Furthermore, we show that targeted data generation by adaptively sampling the parameter space of the generative models gives superior results compared to generating random data points.

This paper presents a novel approach for semantic segmentation of building roof in dense urban environment with Deep Convolution Neural Network (DCNN) using imagery acquired by a Chinese Very High Resolution (VHR) satellite mission, i.e. GaoFen-2 (GF-2). To provide an operational end-to-end work flow for accurate build roof mapping with feature extraction as well as image segmentation, a fully convolutional DCNN with both convolutional and deconvolutional layers is designed to perform the VHR image analysis for labeling pixels. Since the diverse urban patterns and building styles in large areas, sample image data sets of building roof and non-building roof are collected over different metropolitan regions in China. We selected typical cities with dense urban environment in each metropolitan region as study areas for collecting training and test samples. High performance cluster with GPU-mounted workstations is employed to perform the model training and optimization. With the building roof samples collected over different cities, the predictive model with multiple NN layers is developed for building roof labeling. The validation of the building roof map shows that the overall accuracy(OA) and the mean Intersection Over Union( mIOU) of DCNN based segmentation are 94.67%, 0.85 respectively, while CRF-refined segmentation achieved OA of 94.69% and mIOU of 0.83. The results suggest that the proposed approach is a promising solution for building roof mapping with VHR images over large areas across different urban and building patterns. With the operational acquisition of GF2 VHR imagery, it is expected to develop an automated pipeline for operational built-up area monitoring and timely update of building roof map over large areas.

Detector-based spectral CT offers the possibility of obtaining spectral information from which discrete acquisitions at different energy levels can be derived, yielding so-called virtual monoenergetic images (VMI). In this study, we aimed to develop a jointly optimized deep learning framework based on dual-energy CT pulmonary angiography (DE-CTPA) data to generate synthetic monoenergetic images (SMI) for improving automatic pulmonary embolism (PE) detection in single-energy CTPA scans. For this purpose, we used two data sets: our institutional DE-CTPA data set D1 comprising polyenergetic arterial series and the corresponding VMI at low-energy levels (40 keV) with 7,892 image pairs, and a 10% subset of the 2020 RSNA Pulmonary Embolism Detection Challenge data set D2, which consisted of 161,253 polyenergetic images with dichotomous slice-wise annotations (PE/no PE). We trained a fully convolutional encoder-decoder on D1 to generate SMI from single-energy CTPA scans of D2, which were then fed into a ResNet50 network for training of the downstream PE classification task. The quantitative results on the reconstruction ability of our framework revealed high-quality visual SMI predictions with reconstruction results of 0.984 ± 0.002 (structural similarity) and 41.706 ± 0.547 dB (peak-signal-to-noise ratio). PE classification resulted in an AUC of 0.84 for our model, which achieved improved performance compared to other naive approaches with AUCs up to 0.81. Our study stresses the role of using joint optimization strategies for deep learning algorithms to improve automatic PE detection. The proposed pipeline may prove to be beneficial for computer-aided detection systems and could help rescue CTPA studies with suboptimal opacification of the pulmonary arteries from single-energy CT scanners.

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.

One of the critical tools for early detection and subsequent evaluation of the incidence of lung diseases is chest radiography. At a time when the speed and reliability of results, especially for COVID-19 positive patients, is important, the development of applications that would facilitate the work of untrained staff involved in the evaluation is also crucial. Our model takes the form of a simple and intuitive application, into which you only need to upload X-rays: tens or hundreds at once. In just a few seconds, the physician will determine the patient's diagnosis, including the percentage accuracy of the estimate. While the original idea was a mere binary classifier that could tell if a patient was suffering from pneumonia or not, in this paper we present a model that distinguishes between a bacterial disease, a viral infection, or a finding caused by COVID-19. The aim of this research is to demonstrate whether pneumonia can be detected or even spatially localized using a uniform, supervised classification.

Advancements in deep learning and availability of medical imaging data have led to use of CNN based architectures in disease diagnostic assisted systems. In spite of the abundant use of reverse transcription-polymerase chain reaction (RT-PCR) based tests in COVID-19 diagnosis, CT images offer an applicable supplement with its high sensitivity rates. Here, we study classification of COVID-19 pneumonia (CP) and non-COVID-19 pneumonia (NCP) in chest CT scans using efficient deep learning methods to be readily implemented by any hospital. We report our deep network framework design that encompasses Convolutional Neural Networks (CNNs) and bidirectional Long Short Term Memory (biLSTM) architectures. Our study achieved high specificity (CP: 98.3%, NCP: 96.2% Healthy: 89.3%) and high sensitivity (CP: 84.0%, NCP: 93.9% Healthy: 94.9%) in classifying COVID-19 pneumonia, non-COVID-19 pneumonia and healthy patients. Next, we provide visual explanations for the CNN predictions with gradient-weighted class activation mapping (Grad-CAM). The results provided a model explainability by showing that Ground Glass Opacities (GGO), indicators of COVID-19 pneumonia disease, were captured by our CNN network. Finally, we have implemented our approach in three hospitals proving its compatibility and efficiency.

Pedestrian object detection plays a significant role in intelligent systems such as intelligent traffic and monitoring. Traditional machine learning methods on pedestrian detection have shown various drawbacks, \eg{} low accuracy, slow speed, \etc The Convolutional Neural Network (CNN) based object detection algorithms have demonstrated remarkable advantages in the field of pedestrian detection. However, the mainstream CNNs still face the problems of slow speed and low detection accuracy, especially on small and occluded targets from aerial perspective. In this paper, we propose Multi-Scale Attention YOLO (MSA-YOLO) detection algorithm to address the above issues. MSA-YOLO includes a Squeeze, Excitation and Cross Stage Partial (SECSP) channel attention module for CNNs to extract richer pedestrian features with a small number of extra parameters. It also contains a multi-scale prediction module to capture the information among different pedestrian scales, which can recognize the small objects with higher accuracy and significantly reduce the missed detection. To sufficiently evaluate our proposed model, we manually collect and annotate a new benchmark dataset, Luoyang Pedestrian Dataset \footnote{The dataset can be downloaded through this anonymous link: \url{https://drive.google.com/drive/folders/13po1FX7Qk5RDgb60-dzOi74cq_kqDJtM?usp=sharing} }, which has much more sample annotations, features, scenes and image view angles than the existing benchmark datasets. In addition, the images in our dataset have higher resolution than most of benchmark pedestrian detection datasets, which can provide more detailed features of pedestrians and thus improve the model performance. When tested on Luoyang Pedestrian Dataset, our proposed MSA-YOLO algorithm significantly outperform the most commonly used baseline models with almost the same model size. This shows the efficiency of our proposed model. (The code and new dataset will be released to the public later.)

This paper presented a feature vector using a different statistical texture analysis of brain tumor from MRI image. The statistical feature texture is computed using GLCM (Gray Level Co-occurrence Matrices) of Brain Nodule structure. For this paper, the brain nodule segmented using strips method to implemented marker watershed image segmentation based on PSO (Particle Swarm Optimization) and Fuzzy C-means clustering (FCM). Furthermore, the four angles 0^o, 45^o, 90^o and 135^o are calculated the segmented brain image in GLCM. The four angular directions are calculated using texture features are correlation, energy, contrast and homogeneity. The texture analysis is performed a different types of images using past years. So the algorithm proposed statistical texture features are calculated for iterative image segmentation. These results show that MRI image can be implemented in a system of brain cancer detection.

Reliable estimates of poplar plantations area are not available at the French national scale due to the unsuitability and low update rate of existing forest databases for this short-rotation species. While supervised classification methods have been shown to be highly accurate in mapping forest cover from remotely sensed images, their performance depends to a great extent on the labelled samples used to build the models. In addition to their high acquisition cost, such samples are often scarce and not fully representative of the variability in class distributions. Consequently, when classification models are applied to large areas with high intra-class variance, they generally yield poor accuracies. In this paper, we propose the use of active learning (AL) to efficiently adapt a classifier trained on a source image to spatially distinct target images with minimal labelling effort and without sacrificing classification performance. The adaptation consists in actively adding to the initial local model, new relevant training samples from other areas, in a cascade that iteratively improves the generalisation capabilities of the classifier, leading to a global model tailored to different areas. This active selection relies on uncertainty sampling to directly focus on the most informative pixels for which the algorithm is the least certain of their class labels. Experiments conducted on Sentinel-2 time series showed that when the same number of training samples was used, active learning outperformed passive learning (random sampling) by up to 5% of overall accuracy and up to 12% of class F-score. In addition, and depending on the class considered, the random sampling required up to 50% more samples to achieve the same performance of an active learning-based model. Moreover, the results demonstrate the suitability of the derived global model to accurately map poplar plantations among other tree species with overall accuracy values up to 14% higher than those obtained with local models. The proposed approach paves the way for national-scale mapping in an operational context.

It is one of very important and basic problem in compute vision field that recovering depth information of objects from two-dimensional images. In view of the shortcomings of existing methods of depth estimation, a novel approach based on SIFT (the Scale Invariant Feature Transform) is presented in this paper. The approach can estimate the depths of objects in two images which are captured by an un-calibrated ordinary monocular camera. In this approach, above all, the first image is captured. All of the camera parameters remain unchanged, and the second image is acquired after moving the camera a distance d along the optical axis. Then image segmentation and SIFT feature extraction are implemented on the two images separately, and objects in the images are matched. Lastly, an object depth can be computed by the lengths of a pair of straight line segments. In order to ensure that the best appropriate a pair of straight line segments are chose and reduce the computation, the theory of convex hull and the knowledge of triangle similarity are employed. The experimental results show our approach is effective and practical.

Due to an increase in the number of image achieves, Content-Based Image Retrieval (CBIR) has gained attention for research community of computer vision. The image visual contents are represented in a feature space in the form of numerical values that is considered as a feature vector of image. Images belonging to different classes may contain the common visuals and shapes that can result in the closeness of computed feature space of two different images belonging to separate classes. Due to this reason, feature extraction and image representation is selected with appropriate features as it directly affects the performance of image retrieval system. The commonly used visual features are image spatial layout, color, texture and shape. Image feature space is combined to achieve the discriminating ability that is not possible to achieve when the features are used separately. Due to this reason, in this paper, we aim to explore the low-level feature combination that are based on color and shape features. We selected color moments and color histogram to represent color while shape is represented by using invariant moments. We selected this combination, as these features are reported intuitive, compact and robust for image representation. We evaluated the performance of our proposed research by using the Corel, Coil and Ground Truth (GT) image datasets. We evaluated the proposed low-level feature fusion by calculating the precision, recall and time required for feature extraction. The precision, recall and feature extraction values obtained from the proposed low-level feature fusion outperforms the existing research of CBIR.

The objectives of this paper are to investigate the tradeoffs between a physically constrained neural network and a deep, convolutional neural network and to design a combined ML approach ("VarioCNN"). Our solution is provided in the framework of a cyberinfrastructure that includes a newly designed ML software, GEOCLASS-image, modern high-resolution satellite image data sets (Maxar WorldView data) and instructions/descriptions that may facilitate solving similar spatial classification problems. Combining the advantages of the physically-driven connectionist-geostatistical classification method with those of an efficient CNN, VarioCNN provides a means for rapid and efficient extraction of complex geophysical information from submeter resolution satellite imagery. A retraining loop overcomes the difficulties of creating a labeled training data set. Computational analyses and developments are centered on a specific, but generalizable, geophysical problem: The classification of crevasse types that form during the surge of a glacier system. A surge is a glacial catastrophe, an acceleration of a glacier to typically 100-200 times its normal velocity. GEOCLASS-image is applied to study the current (2016-2024) surge in the Negribreen Glacier System, Svalbard. The geophysical result is a description of the structural evolution and expansion of the surge, based on crevasse types that capture ice deformation in six simplified classes.

The objective to fast-track the mapping and registration of large numbers of unrecorded land rights globally, leads to the experimental application of Artificial Intelligence (AI) in the domain of land administration, and specifically the application of automated visual cognition techniques for cadastral mapping tasks. In this research, we applied and compared the ability of rule-based systems within Object Based Image Analysis (OBIA), as opposed to human analysis, to extract visible cadastral boundaries from Very high resolution (VHR) World View-2 image, in both rural and urban settings. From our experiments, machine-based techniques were able to automatically delineate a good proportion of rural parcels with explicit polygons where the correctness of the automatically extracted boundaries was 47.4% against 74.24% for humans and the completeness of 45% for machine, as against 70.4% for humans. On the contrary, in the urban area, automatic results were counterintuitive: even though urban plots and buildings are clearly marked with visible features such as fences, roads and tacitly perceptible to eyes, automation resulted in geometrically and topologically poorly structured data, that could neither be geometrically compared with human digitised, nor actual cadastral data from the field. These results provide an updated snapshot with regards to the performance of contemporary machine-drive feature extraction techniques compared to conventional manual digitising.

Hyperspectral anomaly detection is to recognize anomalies from complex scene in an unsupervised way. Currently, many spectral-spatial detection methods have been proposed with a cascaded manner. However, they often neglect complementary characteristics between spectral and spatial dimensions, which easily leads to yield high false alarm rate. To alleviate this issue, a spectral-spatial information fusion (SSIF) method is designed for hyperspectral anomaly detection. First, an isolation forest is exploited to obtain spectral anomaly map, in which the object-level feature is constructed with entropy rate segmentation algorithm. Then, a local spatial saliency detection scheme is proposed to produce spatial anomaly result. Finally, the spectral and spatial anomaly scores are integrated together followed by a domain transform recursive filtering to generate the final detection result. Experiments on five hyperspectral datasets prove that the proposed SSIF produces superior detection result over other state-of-the-art detection techniques.

With the rapid development of satellite remote sensing technology, the volume of image datasets in many application areas is growing exponentially and the demand for Land-Cover and Land-Use change remote sensing data is growing rapidly. It is thus becoming hard to efficiently and intelligently retrieve the change information that users need from massive image databases. In this paper, content-based image retrieval is successfully applied to change detection and a content-based remote sensing image change information retrieval model is introduced. First, the construction of a new model framework for change information retrieval in a remote sensing database is described. Then, as the target content cannot be expressed by one kind of feature alone, a multiple-feature integrated retrieval model is proposed. Thirdly, an experimental prototype system that was set up to demonstrate the validity and practicability of the model is described. The proposed model is a new method of acquiring change detection information from remote sensing imagery and so can reduce the need for image pre-processing, deal with problems related toseasonal changes as well as other problems encountered in the field of change detection. Meanwhile, the new model has important implications for improving remote sensing image management and autonomous information retrieval.

This paper proposes a new approach for multi-focus images fusion based on Region Mosaicing on Contrast Pyramids (REMCP). A density-based region growing method is developed to construct a focused region mask for multi-focus images. The segmented focused region mask is decomposed into a mask pyramid, which is then used for supervised region mosaicking on a contrast pyramid. In this way, the focus measurement and the continuity of focused regions are incorporated and the pixel level pyramid fusion is improved at the region level. Objective and subjective experiments show that the proposed REMCP is more robust to noise than compared algorithms and can fully preserves the focus information of the multi-focus images meanwhile reducing distortions of the fused images.

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.

Self-supervised learning is a method that learns general representation from unlabeled data. Masked image modeling (MIM), one of the generative self-supervised learning methods, has drawn attention showing state-of-the-art performance on various downstream tasks, though showing poor linear separability resulting from the token-level approach. In this paper, we propose a contrastive learning-based multi-view masked autoencoder for MIM, exploiting an image-level approach by learning common features from two different augmented views. We strengthen MIM by learning long-range global patterns from contrastive loss. Our framework adopts simple encoder-decoder architecture, learning rich and general representation by following a simple process: 1) two different views are generated from an input image with random masking and by contrastive loss, we can learn semantic distance of the representations generated by an encoder. By applying a high mask ratio, 80%, it works as strong augmentation and alleviates the representation collapse problem. 2) With reconstruction loss, decoder learns to reconstruct an original image from the masked image. We assess our framework by several experiments on benchmark datasets of image classification, object detection, and semantic segmentation. We achieve 84.3% fine-tuning accuracy on ImageNet-1K classification and 76.7% in linear probing, exceeding previous studies and show promising results on other downstream tasks. Experimental results demonstrate that our work can learn rich and general image representation by applying contrastive loss to masked image modeling.

Generative models have recently gained popularity in Remote Sensing, offering substantial benefits for interpreting and utilizing satellite imagery across diverse applications such as climate monitoring, urban planning, and wildfire detection. These models are particularly adept at addressing the challenges posed by satellite images, which often exhibit domain variability due to seasonal changes, sensor characteristics, and especially variations in spectral bands. Such variability can significantly impact model performance across various tasks. In response to these challenges, our work introduces a novel approach that harnesses the capabilities of Generative Adversarial Networks (GANs), augmented with Contrastive Learning, to generate target domain images that account for multi-spectral band variations effectively. By maximizing mutual information between corresponding patches and leveraging the power of GANs, our model aims to generate realistic-looking images across different multi-spectral domains. We present a comparative analysis of our model against other well-established generative models, demonstrating its efficacy in generating high-quality satellite images while effectively managing domain variations inherent to multi-spectral diversity.

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.

This paper develops a multi-task learning framework that attempts to incorporate the image structure knowledge to assist image inpainting, which is not well explored in previous works. The primary idea is to train a shared generator to simultaneously complete the corrupted image and corresponding structures --- edge and gradient, thus implicitly encouraging the generator to exploit relevant structure knowledge while inpainting. In the meantime, we also introduce a structure embedding scheme to explicitly embed the learned structure features into the inpainting process, thus to provide possible preconditions for image completion. Specifically, a novel pyramid structure loss is proposed to supervise structure learning and embedding. Moreover, an attention mechanism is developed to further exploit the recurrent structures and patterns in the image to refine the generated structures and contents. Through multi-task learning, structure embedding besides with attention, our framework takes advantage of the structure knowledge and outperforms several state-of-the-art methods on benchmark datasets quantitatively and qualitatively.

Speckle noise is one of the most difficult noises to remove especially in medical applications. It is a nuisance in ultrasound imaging systems which is used in about half of all medical screening systems. Thus, noise removal is an important step in these systems, thereby creating reliable, automated, and potentially low cost systems. Herein, a generalized approach MFNR (Multi-Frame Noise Removal) is used, which is a complete Noise Removal system using KDE (Kernal Density Estimation). Any given type of noise can be removed if its probability density function (PDF) is known. Herein, we extracted the PDF parameters using KDE. Noise removal and detail preservation are not contrary to each other as the case in single-frame noise removal methods. Our results showed practically complete noise removal using MFNR algorithm compared to standard noise removal tools. The Peak Signal to Noise Ratio (PSNR) performance was used as a comparison metric. This paper is an extension to our previous paper where MFNR Algorithm was showed as a general purpose complete noise removal tool for all types of noises

People are drawn to woodcut-style designs due to their striking visual impact and strong contrast. However, traditional woodcut prints and previous computer-aided methods have not addressed the issues of dwindling design inspiration, lengthy production times, and complex adjustment procedures. We propose a novel network framework, the Woodcut-style Design Assistant Network (WDANet), to tackle these challenges. Notably, our research is the first to utilize diffusion models to streamline the woodcut-style design process. We've curated the Woodcut-62 dataset, featuring works from 62 renowned historical artists, to train WDANet in absorbing and learning the aesthetic nuances of woodcut prints, offering users a wealth of design references. Based on a noise reduction network, our dual cross-attention mechanism effectively integrates text and woodcut-style image features. This allows users to input or slightly modify a text description to quickly generate accurate, high-quality woodcut-style designs, saving time and offering flexibility. As confirmed by user studies, quantitative and qualitative analyses show that WDANet outperforms the current state-of-the-art in generating woodcut-style images and proves its value as a design aid.

Underwater image processing faces significant challenges due to the absorption and scattering of light as it travels through water. A self-supervised learning network based on the self-attention mechanism is proposed for underwater visual applications in this paper. The goal is to improve the effectiveness and stability of feature extraction from underwater images. By incorporating self-attention mechanism, the sensitivity of the original network architecture to degraded features of blurred underwater images is enhanced. The network proposed in this paper is trained using transfer learning and evaluated on various underwater image datasets. With distributive, quantitative, and qualitative advantages compared with other methods, experimental results have demonstrated that the algorithm presented shows a slighter decline in feature extraction ability for blurred images as the turbidity of water increases.

In research applications across several areas, noise removal is indispensable for accuracy of final results. Noise is caused due to physical principals, such as background electronic noise, quantum effect, and wave rebound effect to name a few. Noise removal can help improve results in medical, astronomy, defense, and numerous other fields. Addressing this limitation would result in potentially low cost, automatic, and reliable systems. In this paper, a generalized new approach i.e. Multi-Frame Noise Removal (MFNR) is proposed for noise removal. Given any type of data, the probability density function (PDF) of the noise can be determined. Herein, we extracted the noise PDF parameters using KDE (Kernel Density Estimation). Because the data is corrupted by “deterministic” noise, hence can be cleaned. This could be used as a general purpose noise removal tool. The data point with same position in multiple frames helps us determine the noise PDF characteristics and hence making it possible to remove noise. The conventional wisdom which states that noise removal and detail preservation are contrary to each other is not true for MFNR. Experimental results validate our proposed method which showed practically complete noise reduction based on number of frames used, as compared to existing benchmark methods.

Direct georeferencing of airborne pushbroom scanner data usually suffers from the limited precision of navigation sensors onboard of the aircraft. The bundle adjustment of images and orientation parameters, used to perform geocorrection of frame images during the post-processing phase, cannot be used for pushbroom cameras without difficulties: it relies on matching corresponding points between scan lines, which is not feasible in the absence of sufficient overlap and texture information. We address this georeferencing problem by equipping our aircraft with both a frame camera and a pushbroom scanner: the frame images and the navigation parameters measured by a couple GPS/Inertial Measurement Unit (IMU) are input to a bundle adjustment algorithm; the output orientation parameters are used to project the scan lines on a Digital Elevation Model (DEM) and on an orthophoto generated during the bundle adjustement step; using the image feature matching algorithm Speeded Up Robust Features (SURF), corresponding points between the image formed by the projected scan lines and the orthophoto are matched, and through a least-squares method, the boresight between the two cameras is estimated and included in the calculation of the projection; finally, using Particle Image Velocimetry (PIV) on the gradient image, the projection is deformed into a final image that fits the geometry of the orthophoto. We apply this algorithm to five test acquisitions over Lake Geneva region (Switzerland) and Lake Baikal region (Russia). The results are quantified in terms of Root Mean Square Error (RMSE) between matching points of the RGB orthophoto and the pushbroom projection. From a first projection where the Interior Orientation Parameters (IOP) are known with limited precision and the RMSE goes up to 41 pixels, our geocorrection estimates IOP, boresight and Exterior Orientation Parameters (EOP) and produces a new projection which RMSE with the reference orthophoto is around two pixels.

Containing hundreds of spectral bands (features), hyperspectral images (HSIs) have high ability in discrimination of land cover classes. Traditional HSIs data processing methods consider the same importance for all bands in the original feature space (OFS), while different spectral bands play different roles in identification of samples of different classes. In order to explore the relative importance of each feature, we learn a weighting matrix and obtain the relative weighted feature space (RWFS) as an enriched feature space for HSIs data analysis in this paper. To overcome the difficulty of limited labeled samples which is common case in HSIs data analysis, we extend our method to semisupervised framework. To transfer available knowledge to unlabeled samples, we employ graph based clustering where low rank representation (LRR) is used to define the similarity function for graph. After construction the RWFS, any arbitrary dimension reduction method and classification algorithm can be employed in RWFS. The experimental results on two well-known HSIs data set show that some dimension reduction algorithms have better performance in the new weighted feature space.

Automatic target detection of remote sensing images (RSI) plays an important role in military reconnaissance, disaster monitoring, and target rescue. The core task of remote sensing target detection is to judge the target categories and complete precise location. However, the existing target detection algorithms have limited accuracy and weak generalization capability for remote sensing images with complex backgrounds. To achieve accurate detection of different categories targets in remote sensing images, this study presents a novel feature enhancement single shot multibox detector (FESSD) algorithm for remote sensing target detection. The FESSD introduces feature enhancement module and attention mechanism into the convolution neural networks (CNN) model, which can effectively enhance the feature extraction ability and nonlinear relationship between different convolution features. Specifically, the feature enhancement module is used to extract the multi-scale feature information, and enhance the model nonlinear learning ability; the self-learning attention mechanism (SAM) is used to expand the convolution kernel local receptive field, which makes the model extract more valuable features. In addition, the nonlinear relationship between different convolution features is enhanced using the feature pyramid attention mechanism (PAM). The advantage of FESSD over other state-of-the-art target detection methods is validated by experiments on the presented seven-class target detection dataset (SD-RSI) and the public DIOR dataset.

With the development of remote sensing satellite technology for Earth observation, remote sensing stereo images have been used for three-dimensional reconstruction in various fields, such as urban planning and construction. However, remote sensing images often include noise, occluded regions, weakly textured areas and repeated textures, which can lead to reduced accuracy in stereo matching and affect the quality of the 3D reconstruction results. To reduce the impact of complex scenes in remote sensing images on stereo matching and to ensure both speed and accuracy, we propose a new end-to-end stereo matching network based on convolutional neural networks (CNNs). The proposed stereo matching network can learn features at different scales from the original images and construct cost volumes with varying scales to obtain richer scale information. Additionally, when constructing the cost volume, we introduce negative disparity to adapt to the common occurrence of both negative and nonnegative disparities in remote sensing stereo image pairs. For cost aggregation, we employ a 3D convolution-based encoder-decoder structure that allows the network to adaptively aggregate information. Before feature aggregation, we also introduce an attention module to retain more valuable feature information, enhance feature representation, and obtain a higher-quality disparity map. By training on the publicly available US3D dataset, we obtain the accuracy that 1.115 pixel in end-point error (EPE) and 5.32% in the error pixel ratio (D1) on the test dataset, and the inference speed is 92 ms. Comparing our model with existing state-of-the-art models, we achieve higher accuracy, and the network is beneficial for the three-dimensional reconstruction of remote sensing images.

This work tackles the problem of image restoration, a crucial task in many fields of applied sciences, focusing on removing degradation caused by blur and noise during the acquisition process. Drawing inspiration from the multi-penalty approach based on the Uniform Penalty principle introduced in [Bortolotti et al. arXiv.math.NA/2309.14163], we develop here a new image restoration model and an iterative algorithm for its effective solution. The model incorporates pixel-wise regularization terms and establishes a rule for parameters selection, aiming to restore images through the solution of a sequence of constrained optimization problems. To achieve this, we present a modified version of the Newton Projection method, adapted to multi-penalty scenarios, and prove its convergence. Numerical experiments demonstrate the efficacy of the method in eliminating noise and blur while preserving the image edges.

Background: Assessing body image and personalized rehabilitation in lower limb amputation is essential to measure impact on an individual’s quality of life and psychosocial wellbeing. The aim of this study was to develop a Spanish version of the Amputee Body Image Scale (ABIS-E) for Spanish-speaking lower limb amputee. Methods: A cross-sectional study was conducted including amputee patients in local in Madrid, Spain. Clinical outcomes about body image (Amputee Body Image Scale, ABIS), health-related quality of life (EuroQol-5D-5L), depression and anxiety (Hospital Anxiety and Depression Scale, HADS), pain (Brief Pain Inventory-Short Form, BPI-SF) and functional capacity (Prosthesis Evaluation Questionnaire, PEQ) were collected. Results: Seventy-three participants were assessed. Excellent test-retest reliability (ICC=0.847) and good internal consistency (Cronbach's alpha=0.753) were obtained. Three factors were extracted in the factor analyses. Convergent validity with Pearson's and Spearman's correlation coefficients were calculated for the depression and anxiety questionnaires (HADS) (values between .57 and .67), functional capacity (PEQ) (values between -.35 and .71) and quality of life (EQ-5D-5L) (values between -.37 and .61). Conclusions: The ABIS-E is a reliable and valid tool for measuring body image in the Spanish population with a lower limb amputation, potentially useful in primary care to identify psychosocial problems.

Document deskewing is a fundamental problem in document image processing. While existing methods have limitations, such as Hough Line Transformation that can deskew images upside down, and Deep Learning models that require huge amounts of human labour and computational resources and still fail to deskew while taking care of orientation, OCR-based methods also struggle to read text when it is tilted. In this paper, we propose a novel, simple, cost-effective deep learning method for fixing the skew and orientation of documents. Our approach reduces the search space for the machine learning model to predict whether an image is upside down or not, avoiding the huge search space of predicting an angle between 0 and 360. We finetuned a MobileNetV2 model, which was pre-trained on imagenet, using only 200 images and achieve good results. This method is useful for automation-based tasks, such as data extraction using OCR technology, and can greatly reduce manual labour.

Body-Esteem Scale is an assessment tool for adolescents and adults that evaluate three dimensions of self-evaluations of one’s body. Body-Esteem Scale has been translated and validated in some countries since America down to Europe. Lack of translation and reliability evidence in Portugal was detected. This study aimed to translate and test the validity and reliability of the Body Esteem Scale for Adolescents and Adults (BESAA) in students in the context of Portuguese higher educa-tion. A total of 173 students (60.7% are female) with a mean age of 19.7 (standard deviation = 2.2) years participated. Categorical Principal Component Analysis was used to assess the underlying dimensions of BESAA. Construct validity was evaluated through correlation with the Appearance Schemas Inventory – Revised and a three-factor model (“Appearance”, ‘‘Weight’’ and “Attribu-tion’’) was established. Confirmatory factor analysis was performed to verify the construct validity of the instrument. Items that had factor weights (λ)<.40 were removed, as well as those that were considered redundant by the modification indices estimated by the Lagrange Multipliers (LM) method (LM>11, p<.001). We observed high correlations between theoretically similar factors, and low correlations between different factors. The Portuguese BESAA showed adequate validity and reliability.

A 'little brother' of pain, itch is an unpleasant sensation that creates a specific urge to scratch. To date, various machine-learning based image classifiers (MBICs) have been proposed for quantitative analysis of itch-induced scratch behaviour of laboratory animals in an automated, non-invasive, inexpensive and real-time manner. In spite of MBICs' advantages, the overall performances (accuracy, sensitivity and specificity) of current MBIC approaches remains inconsistent, with their values varying from ~50% to ~99%, for which the reasons underlying have yet to be investigated further, both computationally and experimentally. To look into the variation of the performance of MBICs in automated detection of itch-induced scratch, this article focuses on the experimental data recording step, and reports here for the first time that MBICs' overall performance is inextricably linked to the sharpness of experimentally recorded video of laboratory animal scratch behaviour. This article furthermore demonstrates for the first time that a linearly correlated relationship exists between video sharpness and overall performance (accuracy and specificity, but not sensitivity) of MBICs, and highlight the primary role of experimental data recording in rapid, accurate and consistent quantitative assessment of laboratory animal itch.

The semantic segmentation of high-resolution remote sensing images (HR-RSI) is crucial for a wide range of applications, such as precision agriculture, urban planning, natural resource assessment, and ecological monitoring. However, accurately classifying pixels in HR-RSI faces challenges due to densely distributed small objects and scale variations. Existing techniques, including Convolutional Neural Networks (CNNs) and other methods for hierarchical feature extraction and fusion of remote sensing image, often do not achieve the desired accuracy. In this paper, we propose a novel approach called the Hierarchical Rich-scale Fusion Network (HRFNet) to address these challenges. HRFNet utilizes advanced information rating and image partition techniques to extract rich-scale features within image layers. This allows for the adaptive exploration of both local and global contextual information. Moreover, we introduce a structured intra-layer to inter-layer feature aggregation module, which enables the adaptive extraction of fine-grained details and high-level semantic information from multi-layer feature maps in a highly flexible manner. Extensive experimentation has been conducted to validate the effectiveness of our proposed method. Our results demonstrate that HRFNet outperforms existing techniques, achieving state-of-the-art (SOTA) results on benchmark datasets, specifically the ISPRS Potsdam and Vaihingen datasets.

Aerial image classification has become popular and has attracted extensive research efforts in recent decades. The main challenge lies in its very high spatial resolution but relatively insufficient spectral information. To this end, spatial-spectral feature extraction is a popular strategy for classification. However, parameter determination for that feature extraction is usually time-consuming and depends excessively on experience. In this paper, an automatic spatial feature extraction approach based on image raster and segmental vector data cross-analysis is proposed for the classification of very high spatial resolution (VHSR) aerial imagery. First, multi-resolution segmentation is used to generate strongly homogeneous image objects and extract corresponding vectors. Then, to automatically explore the region of a ground target, two rules, which are derived from Tobler’s First Law of Geography (TFL) and a topological relationship of vector data, are integrated to constrain the extension of a region around a central object. Third, the shape and size of the extended region are described. A final classification map is achieved through a supervised classifier using shape, size, and spectral features. Experiments on three real aerial images of VHSR (0.1 to 0.32 m) are done to evaluate effectiveness and robustness of the proposed approach. Comparisons to state-of-the-art methods demonstrate the superiority of the proposed method in VHSR image classification.

Grain yield prediction affects policy making in various aspects such as agricultural production planning, food security assurance, and adjustment of foreign trade. Accurately predicting grain yield is of great significance in ensuring global food security. This paper is based on the MODIS remote sensing image data products from 2010 to 2020, and adds band information such as vegetation index and temperature to form composite remote sensing data as a data set. Aiming at the lack of models for large-scale forecasting and the need for human intervention in traditional models, this paper proposes a grain production estimation model based on deep learning. First, image cropping and yield mapping techniques are used to process the data to generate training samples. Then the channel and spatial attention mechanism (Convolutional Block Attention Module, CBAM) is added for extracting spatial information in different remote sensing bands to improve the efficiency of the model. Long Short-Term Memory (LSTM) neural networks is also added to obtain feature information in the time dimension. Finally, a national-scale grain yield prediction model is constructed. The proposed model was tested on data from 2018 to 2020 showing an average R2 of 0.940 and an average RMSE of 80,020 tons, indicating that it can predict Chinese grain yield better. The model proposed in this paper extracts grain yield information directly from the composite remote sensing data, and solves the problem of small-scale research and imprecise yield prediction in an end-to-end manner.

The paper demonstrates the analysis of Corona Virus Disease based on a probabilistic model. It involves a technique for classification and prediction by recognizing typical and diagnostically most important CT images features relating to Corona Virus. The main contributions of the research include predicting the probability of recurrences in no recurrence (first time detection) cases at applying our proposed approach for feature extraction. The combination of the conventional statistical and machine learning tools is applied for feature extraction from CT images through four images filters in combination with proposed composite hybrid feature extraction (CHFS). The selected features were classified by the stack hybrid classification system(SHC). Experimental study with real data demonstrates the feasibility and potential of the proposed approach for the said cause.

Machine Learning has completely transformed health care system, which transmits medical data through IOT sensors. So it is very important to encrypt them to protect patient data. encrypting medical images from a performance perspective consumes time; hence the use of an auto encoder is essential. An auto encoder is used in this work to compress the image as a vector prior to the encryption process. The digital image passes across description function and a decoder to get back the image in the proposed work; various experiments are carried out on hyper parameters to achieve the highest outcome of the classification. The findings demonstrate that the combination of Mean Square Logarithmic Error as the loss function, ADA grad as an optimizer, two layers for the encoder, and another reverse for the decoder, RELU as the activation function generates the best auto encoder results. The combination of Mean square error (lose function), RMS prop (optimizer), three layers for the encoder and another reverse for the decoder, and RELU (activation function) has the best classification result. All the experiments with different hyper parameter has run almost very close to each other even when changing the number of layers. The running time is between 9 and 16 second for each epoch.