Two of the most common activation functions (AF) in deep neural networks (DNN) training are Sigmoid and ReLU. Sigmoid was tend to be more popular the previous decades, but it was suffering with the common vanishing gradient problems. ReLU has resolved these problems by using zero gradient and not tiny values for negative weights and the value “1” for all positives. Although it significant resolves the vanishing of the gradients, it poses new issues with dying neurons of the zero values. Recent approaches for improvements are in a similar direction by just proposing variations of the AF, such as Leaky ReLU (LReLU), while maintaining the solution within the same unresolved gradient problems. In this paper, the combining of the Sigmoid and ReLU in one single function is proposed, as a way to take the advantages of the two. The experimental results demonstrate that by using the ReLU’s gradient solution on positive weights, and Sigmoid’s gradient solution on negatives, has a significant improvement on performance of training Neural Networks on image classification of diseases such as COVID-19, text and tabular data classification tasks on five different datasets.

The fusion of global contextual information with local cropped block details is crucial for segmenting ultra-high resolution images. In this study, we introduce a novel fusion mechanism termed Global-Local Deep Fusion (GL-Deep Fusion) based on an enhanced transformer architecture, which efficiently integrates global contextual information and local details. Specifically, we propose the Global-Local Synthesis Networks (GLSNet), a dual-branch network where one branch processes the entire original image, while the other branch handles cropped local patches as input. The feature fusion of different branches in GLSNet is achieved through GL-Deep Fusion, significantly enhancing the accuracy of ultra-high resolution image segmentation. Particularly effective is GLSNet in identifying tiny overlapping items. To optimize GPU memory utilization, we meticulously design a dual-branch architecture that proficiently leverages the features it extracts, seamlessly integrating them into the enhanced transformer framework of GL-Deep Fusion. Extensive experiments conducted on challenging benchmarks, including DeepGlobe and Vaihingen datasets, demonstrate that GLSNet achieves a new state-of-the-art performance in terms of GPU memory utilization and segmentation accuracy tradeoff.

Railway transportation is one of the main modes of long-distance coal transportation, and it is inevitable to cause environmental pollution during the transportation process. In order to improve the environment along the railway and increase the utilization rate of coal resources, this paper proposes a detection algorithm for scattered coal solidification layer during transportation based on the YOLO v8 model, and designs an intelligent recognition model suitable for coal solidification layer detection devices by combining fluorescence detection methods. Through experimental analysis, the model meets the requirements of practical detection and plays a crucial role in environmental protection, with strong practical application value.

As the fast growth of information technology (IT), the safety of image transmission and the storing of images are increasingly concerned. Traditional image encryption algorithms have certain limitations in transmission and security, so there is an urgent need for a secure and reliable image encryption algorithm. A universal compression sensing (CS) image encryption (IE) algorithm based on DNA-triploid mutation (DTM) is presented in this paper. Firstly, by using CS algorithm an image is compressed while obtaining a range of chaotic sequences by iteration of chaotic map. Then DNA sequences are generated by encoding the image, and based on the DTM, new mutant DNA sequences are generated according to specific rules. Next, the chaotic sequences are operated at the DNA level to do confusion and diffusion operations on the image to ensure the security of the data. At last, DNA decoding is carried out to obtain the compressed-encrypted image. Both simulation experiments and performance tests fully show that a high level of security and reliability of the proposed algorithm in protecting image privacy is achieved.

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.

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.

This paper explores the application of wavelet analysis, a multiscale approach for enhancing visual clarity, in the context of image denoising, which reduces the impact of noisy pixels, caused by various factors such as electronic sensor limitations, low-light conditions, or transmission errors in digital imaging systems. This paper introduces some common noise types like Gaussian noise and processes of image denoising, eliciting the strength of wavelet analysis. As a powerful image denoising technology, wavelet analysis needs five steps to process the image, and the key step is thresholding. There are many kinds of wavelet, and each wavelet has different advantages and functions, which makes it suitable for different applications. Hence, wavelet analysis also makes a contribution in various fields beyond signal processing and data analysis, such as Biomedical Imaging and Geophysics and Seismology, where preserving image quality is essential for accurate analysis and interpretation. In short, this research highlights the promise of wavelet analysis, emphasizing the use of high- quality image data.

Recent technological advances have significantly increased the data volume obtained from deep space exploration missions, making the downlink rate a primary limiting factor. Particularly, JAXA’s Martian Moons eXploration (MMX) mission encounters this problem when identifying safe and scientifically valuable landing sites on Phobos using high-resolution images. A strategic approach in which we effectively reduce image data volumes without compromising essential scientific information is thus required. In this work, we investigate the influence of image data compression, especially as it concerns the accuracy of generating the local Digital Terrain Models (DTMs) that will be used to determine MMX’s landing sites. We obtain simulated images of Phobos that are compressed using the CCSDS-120 with integer/float-point discrete wavelet transform (DWT), candidate algorithms for the MMX mission. Accordingly, we show that, if the compression ratio is 70% or lower, the effect of image compression remains constrained, and local DTMs can be generated within altitude errors of 40 cm on the surface of Phobos, which is ideal for selecting safe landing spots. We conclude that the compression ratio can be increased as high as 70%, and such compression enables us to facilitate critical phases in the MMX mission even with the limited downlink rate.

For Synthetic Aperture Radar (SAR) image registration, successive processes following feature extraction are required by both the traditional feature-based method and the deep learning method. Among these processes, the feature matching process—whose time and space complexity are related to the number of feature points extracted from sensed and reference images, as well as the dimension of feature descriptors—proves to be particularly time-consuming. Additionally, the successive processes introduce data sharing and memory occupancy issues, requiring an elaborate design to prevent memory leaks. To address these challenges, this paper introduces the OptionEM-based reinforcement learning framework to achieve end-to-end SAR image registration. This framework outputs registered images directly without requiring feature matching and calculation of the transformation matrix, leading to significant processing time savings. The Transformer architecture is employed to learn image features, while a correlation network is introduced to learn the correlation and transformation matrix between image pairs. Reinforcement learning, as a decision process, can dynamically correct errors, making it more efficient and robust compared to supervised learning mechanisms like deep learning. We present a hierarchical reinforcement learning framework combined with episodic memory to mitigate the inherent problem of invalid exploration in generalized reinforcement learning algorithms. This approach effectively combines coarse and fine registration, further enhancing training efficiency. Experiments conducted on three sets of SAR images, acquired by TerraSAR-X and Sentinel-1A, demonstrate that the proposed method’s average runtime is sub-second, achieving subpixel registration accuracy.

The dependence on Unmanned Aerial Vehicles (UAVs) has dramatically increased in many sectors around the globe. UAVs are in high demand, and their technology is developing quickly due to their sophisticated ability to handle various issues. UAVs are capable of replacing labor-intensive tasks with conducive and safe regulation. Additional tools or sensors need to be added to the UAVs system to ensure the implementation of UAVs able to serve into industrial level. The paper aims to consolidate and present a thorough understanding of the various stages of image processing pipelines deployed in UAV applications, including image acquisition, preprocessing, feature extraction, object detection and tracking, and decision-making processes. Throughout this paper, several aspects were deliberate such as strengths, limitations, and performance metrics of existing approaches, this paper seeks to provide researchers, engineers, and practitioners with valuable insights into the challenges and opportunities of image processing systems for UAVs. Ultimately, the synthesis of this knowledge will contribute to enhancing the effective-ness, autonomy, and applicability of UAVs in diverse fields such as surveillance, agriculture, disaster management, and environmental monitoring.

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.

The widespread availability of digital image processing softwares has given rise to various forms of image manipulation and forgery which can pose a significant challenge in different fields such as law enforcement, journalism etc,. it can also lead a privacy concern. We are proposing a privacy-preserving framework to encrypt images before processing them is vital to maintain the privacy and confidentiality of sensitive images, especially those used for purpose of Investigation. To address these challenges, we propose a novel solution that detects image forgeries while preserving the privacy of the images. Our method proposes a privacy-preserving framework that encrypts the images before processing them, making it difficult for unauthorized individuals to access them. The proposed method utilizes a compression quality analysis in the encrypted domain to detect the presence of forgeries in images if the forged portion (dummy image) has a compression quality different from the original image (featured image) in the encrypted domain. This approach effectively localizes the tampered portions of the image, even for small pixel blocks of size 10x10 in the encrypted domain. Furthermore, the method identifies the featured image's JPEG quality using the first minima in the energy graph.

Shape of supracondylar fracture of the humeral of pediatric patients is analysed with Procrustes method. XR–images of fractures are considered both in anterio-posterior (AP) view (66 images) and in a lateral (L) view (24 images). Applying Procrustes method for both views mean images are constructed and compared. Variability of shapes is quantified with a shape principal component analysis. Non-parametric tests (permutational and bootstrap) do not indicate statistical difference between Procrustes mean shapes in anterio-posterior and lateral projections. It is shown, however, that AP and L shapes of humeral fractures differ in their variability quantified by shape principal components.

We propose an algorithm for generating a panoramic image of a pipe’s inner surface based on inverse perspective mapping (IPM). For efficient crack detection, we used only perspective images of the pipe interior that can be obtained with a single lens camera instead of those taken with a 360-degree camera or a 3D depth camera. Frontal images taken while passing through the pipe were converted to images of the inner surface of the pipe using IPM. We derived a generalized IPM formula that considers the slope of the image plane to correct image distortion caused by the tilt of the plane; this IPM formula was derived based on the vanishing point of the perspective image, which was detected using optical flow techniques. Finally, the multiple transformed images with overlapping areas were combined via image stitching to create a panoramic image of the inner pipe surface. To validate our proposed algorithm, we restored images of pipe inner surface using a 3D pipe model and used these images for crack detection.

The agricultural sector is undergoing a revolution that requires sustainable solutions to the challenges that arise from traditional farming methods. To address these challenges, technical and sustainable support is needed to develop projects that improve crop performance. This study focuses on the onion crop and the challenges presented throughout its phenological cycle. Aerial monitoring using unmanned aerial vehicles (UAV) and digital image processing were used to identify patterns in the onion crop, including humid areas, weed growth, vegetation deficits, and decreased harvest performance. An algorithm was developed to identify the patterns that most affected crop growth, as the average local production reported was 40.166 ton/ha, but only 25.00 ton/ha was reached due to blight caused by constant humidity and limited sunlight. This resulted in the death of leaves and poor development of bulbs, with 50% of the production being of medium size. It is estimated that approximately 20% of the production was lost due to blight and unfavorable weather conditions.

Translation of basic animal research to find effective methods of diagnosing and treating human neurological disorders requires parallel analysis infrastructures. Small animals such as mice provide exploratory animal disease models. However, many interventions developed using small animal models fail to translate to human use due to physical or biological differences. Recently, large-animal minipigs have emerged in neuroscience due to both brain similarity and economic advantages. Medical image processing is a crucial part of research as it allows researchers to monitor their experiments and understand disease development. However, although many algorithms are created and optimized for MR analysis of human data, those tools are not directly applicable or sufficiently sensitive to measure minipig data. In this work, we propose PigSNIPE - a pipeline for the automated handling, processing, and analyzing of large-scale data sets of minipig MR images. The pipeline allows for image registration, AC-PC alignment, landmark detection, skull stripping, brainmasks and intracranial volume segmentation (DICE 0.98), tissue segmentation (DICE 0.82), and caudate-putamen brain segmentation (DICE 0.8) in under two minutes. To the best of our knowledge, this is the first automated pipeline tool aimed at large animal images.

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 single paragraph of about 200 words maximum. For research articles, abstracts should give a pertinent overview of the work. We strongly encourage authors to use the following style of structured abstracts, but without headings: (1) Background: place the question addressed in a broad context and highlight the purpose of the study; (2) Methods: describe briefly the main methods or treatments applied; (3) Results: summarize the article’s main findings; (4) Conclusions: indicate the main conclusions or interpretations. The abstract should be an objective representation of the article, it must not contain results which are not presented and substantiated in the main text and should not exaggerate the main conclusions.

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.

Diatom identification and counting by light microscopy is a fundamental method in ecological and water quality investigations. Here we present a new variant of this method based on “digital virtual slides”, and compare it to the traditional, non-digitized light microscopy workflow. We analysed three replicates of six samples using two methods: 1) working directly on a light microscope (the “traditional” counting method), and 2) preparing “virtual digital slides” by high-resolution slide scanning and subsequently identifying and labelling individual valves or frustules using a web browser-based image annotation platform (the digital method). Both methods led to comparable results in terms of species richness, diatom indices and diatom community composition. Although counting by digital microscopy was slightly more time consuming, our experience points out that the digital workflow can not only improve the transparency and reusability of diatom counts but it can also increase taxonomic precision. The introduced digital workflow can also be applied for taxonomic inter-expert calibration through the web, and for producing training image sets for deep-learning-based diatom identification, making it a promising and versatile alternative or extension to traditional light microscopic diatom analyses in the future.

Boosted by the progress in deep learning, Single Image Super-Resolution (SISR) has gained a lot of interest in the Remote Sensing community, who sees it as an oportunity to compensate for satellite's ever-limited spatial resolution with respect to end users needs. While there has been a great amount of work on network architures in the latest years, deep learning based SISR in remote sensing is still limited by the availability of the large training sets it requires. The lack of publicly available large datasets with the required variability in terms of landscapes and seasons pushes researchers to simulate their own dataset by means of downsampling. This may impair the applicability of the trained model on real world data at the target input resolution. In this paper, we propose an open-data licenced dataset composed of 10m and 20m cloud-free surface reflectance patches from Sentinel-2, with their reference spatially-registered surface reflectance patches at 5 meter resolution acquired on the same day by the VENµS satellite. This dataset covers 29 locations on earth with a total of 132 955 patches of 256x256 pixels at 5 meters resolution, and can be used for the training of super-resolution algorithms to bring the spatial resolution of 8 of the Sentinel-2 bands down to 5 meters.

Brain tissue segmentation is an important component of clinical diagnosis of brain diseases by means of multi-modal magnetic resonance imaging (MR). Brain tissue segmentation is developed by many unsupervised methods in literature. The most commonly used unsupervised methods are: K-Means, Expectation Maximization and Fuzzy Clustering. Fuzzy clustering methods offer considerable benefits compared with the aforementioned methods as they are capable of handling brain images which are complex, largely uncertain and imprecise in nature. However, this approach suffers from the intrinsic noise and intensity inhomogeneity (IIH) in the data resulted from the acquisition process. To resolve these issues, we propose a fuzzy consensus clustering algorithm that defines a membership function resulted from a voting schema to cluster the pixels. In particular, we first pre-process the MRI data and employ several segmentation techniques based on traditional fuzzy sets and intuitionistic sets. Then, we adopted a voting schema to fuse the results of the applied clustering methods. Finally, to evaluate the proposed method, we used the well-known performance measures (boundary measure, overlap measure and volume measure) on two publicly available datasets (OASIS and IBSR18). The experimental results show the superior performance of the proposed method in comparison with the recent state of the arts.

Vegetation status assessment is crucial for agricultural monitoring and management. Vegetation indices derived from high resolution image time series can be used to derive key phenological parameters for annual crops. In this work, we propose a procedure for the estimation of these parameters and their associated uncertainties. The approach uses Bayesian inference through Markov Chain Monte Carlo in order to obtain the full joint posterior distribution of the phenological parameters given the satellite observations. The proposed algorithm is quantitatively validated on synthetic data. Its use on real data is presented together with an application to real-time within season estimation allowing for phenology forecasting.

The use of convolutional neural networks (CNNs) in image classification has become the standard method of approaching computer vision problems. Here we apply pre-trained networks to classify images of non-breaking, plunging and spilling breaking waves. The CNNs are used as basic feature extractors and a classifier is then trained on top of these networks. The dynamic nature of breaking waves is exploited by using image sequences to gain extra information and improve the classification results. We also see improved classification performance in using pre-computed image features such as the optical flow between image pairs. The inclusion of the dynamic information improves the classification between breaking wave classes. We also provide corrections to the methodology from the article from which the data originates to achieve a more accurate assessment of performance.

Background: Zebrafish (Danio rerio) is a model organism emerged for the study of human cancer. Compared with the murine model, the zebrafish model has several properties ideal for personalized therapies. The transparency of the zebrafish embryos and the development of the pigment-deficient “casper” zebrafish line give the capacity to directly observe cancer formation and progression in the living animal. Automatic quantification of cellular proliferation in vivo is critical to the development of personalized medicine. Methods: A new methodology was defined to automatically quantify the cancer cellular evolution. ZFTool was developed to establish a base threshold that eliminates the embryo auto-fluorescence and automatically measures the area and intensity of GFP (green-fluorescent protein) marked cells and define a proliferation index. Results: Proliferation index automatically computed on different targets demonstrates the efficiency of ZFTool to provide a good automatic quantification of cancer cell evolution and dissemination. Conclusion: Our results demonstrate that ZFTool is a reliable tool for the automatic quantification of the proliferation index, being a measure of cancer mass evolution in zebrafish eliminating the influence of its autofluorescence.

Recent neuroscience research results show that the nerve information in the brain is not only encoded by the spatial information. Spiking neural network based on pulse frequency coding plays a very important role in dealing with the problem of brain signal, especially complicated space-time information. In this paper, an unsupervised learning algorithm for bilayer feedforward spiking neural networks based on spike-timing dependent plasticity (STDP) competitiveness is proposed and applied to SAR image classification on MSTAR for the first time. The SNN learns autonomously from the input value without any labeled signal and the overall classification accuracy of SAR targets reached 80.8%. The experimental results show that the algorithm adopts the synaptic neurons and network structure with stronger biological rationality, and has the ability to classify targets on SAR image. Meanwhile, the feature map extraction ability of neurons is visualized by the generative property of SNN, which is a beneficial attempt to apply the brain-like neural network into SAR image interpretation.

This article described the technology of determining earthquake epicenter with radar remote sensing on the example of Sentinel-1A/B. To determine the epicenter of the earthquake, the Earth's crust displacements were analyzed using radar remote sensing data obtained for the ascending and descending flight orbits. Coordinates of Earthquake epicenters were found according to line-of-sight displacement images via its maximum value. Displacement of the Earth's crust was obtained by processing in the GMTSAR package in the VirtualBox virtual machine of the Linux Ubuntu 16.04 operation system. Two earthquakes that occurred in 2020 were studied to determine the accuracy of finding epicenters using the ascending and descending orbits Sentinel-1A/B. These earthquakes occurred in Western Xizang, China, and Doganyol, Turkey. The maximum deviation from the officially registered epicenter coordinates was 15.38 km for Doganyol and 3.2 km for the Western Xizang earthquake. The negative displacement was 90 mm for Doganyol and 50 mm for Western Xizang.

In the present, the growth of digitization and worldwide communications make OCR systems of exotic languages a very important task. In this paper, we attempt to develop an OCR system for one of these exotic languages with a unique script, Amharic. Motivated by the recent success of the Attention mechanism in Neural Machine Translation (NMT), we extend the attention mechanism for Amharic text-image recognition. The proposed model consists of CNNs and attention embedded recurrent encoder-decoder networks that are integrated following the configuration of the seq2seq framework. The attention network parameters are trained in an end-to-end fashion and the context vector is injected, with the previously predicted output, at each time steps of decoding. Unlike the existing OCR model that minimizes the CTC objective function, the new model minimizes the categorical cross-entropy loss. The performance of the proposed attention-based model is evaluated against the test dataset from the ADOCR database which consists of both printed and synthetically generated Amharic text-line images and achieved promising results with a CER of 1.54% and 1.17% respectively.

Precision agriculture is a technology used by farmers to help food sustainability amidst growing population. One of the tools of precision agriculture is yield monitoring, which helps a farmer manage his production. Yield monitoring is usually done during harvest, however it could also be done early in the growing season. Early prediction of yield, specifically for fruit trees, aids the farmer in the marketing of their product and assists in managing production logistics such as labor requirement and storage needs. In this study, a machine vision system is developed to estimate fruit yield early in the season. The machine vision system uses a color camera to capture images of fruit trees during the full bloom period. An image segmentation algorithm based on an artificial neural network was developed to recognize and count the blossoms on the tree. The artificial neural network segmentation algorithm uses color information and position as input. The resulting correlation between the blossom count and the actual number of fruits on the tree shows the potential of this method to be used for early prediction of fruit yield.

This article presents a new method of segmenting images with gray levels. The method is based on determining several thresholds for separation of gray levels. The determination of these thresholds is done using the certainty of the neutrosophic information. The concept of this method can be stated simply: to choose the local maximums for the neutrosophic certainty.

Nutrient estimation in forest ecosystems through satellite images allows us to obtain accurate data, starting with data transformation from forest stands and the existing relationship with the spectral information of the image through modeling. The objective of the study was to quantify and validate the content of C, N, H in aboveground tree biomass in managed stands using spatial modeling and satellite images. This study was conducted during 2017-2018 in managed forest stands in San Juan Lachao, Oaxaca, Mexico. Fifteen 400 m2 experimental sites were selectively established, using a completely randomized experimental design of five silvicultural treatments with three replications. As part of data preprocessing, normality and homogeneity of variances assumptions were checked using the Shapiro-Wilk and Bartlett tests, respectively. From the pixels, data of the average of Normalized Difference Vegetation Index (NDVI) that surrounded the sampling sites were contrasted against the data obtained from forest inventory and the regression models to estimate C, N, H and biomass were generated. Models were validated by NDVI. With the models we estimated 0.95 t ha-1 biomass, which contains between 0.61 and 0.63 of C, 0.44-0.46 of N and 0.24 of H. The models generated had coefficients of determination (R2) of 0.85 to 0.87, which are significant parameters (p ≤ 0.0001). These results confirm that the use of Sentinel satellite images in the estimation of these elements in forest ecosystems based on the relationship between data inventory and the NDVI is highly reliable.

The latest methods based on deep learning have achieved amazing results regarding the complex work of inpainting large missing areas in an image. This type of method generally attempts to generate one single "optimal" inpainting result, ignoring many other plausible results. However, considering the uncertainty of the inpainting task, one sole result can hardly be regarded as a desired regeneration of the missing area. In view of this weakness, which is related to the design of the previous algorithms, we propose a novel deep generative model equipped with a brand new style extractor which can extract the style noise (a latent vector) from the ground truth image. Once obtained, the extracted style noise and the ground truth image are both input into the generator. We also craft a consistency loss that guides the generated image to approximate the ground truth. Meanwhile, the same extractor captures the style noise from the generated image, which is forced to approach the input noise according to the consistency loss. After iterations, our generator is able to learn the styles corresponding to multiple sets of noise. The proposed model can generate a (sufficiently large) number of inpainting results consistent with the context semantics of the image. Moreover, we check the effectiveness of our model on three databases, i.e., CelebA, Agricultural Disease, and MauFlex. Compared to state-of-the-art inpainting methods, this model is able to offer desirable inpainting results with both a better quality and higher diversity. The code and model will be made available on https://github.com/vivitsai/SEGAN.

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.

In the fashion field, the use of electroplated small metal parts such as studs, clips and buckles is widespread. The plate is often made of precious metal, such as gold or platinum. Due to the high cost of these materials, it is strategically relevant and of primary importance for manufacturers to avoid any waste by depositing only the strictly necessary amount of material. To this aim, Companies need to be aware of the overall number of items to be electroplated so that it is possible to properly set the parameters driving the galvanic process. Accordingly, the present paper describes a Machine Vision-based method able to automatically count small metal parts arranged on a galvanic frame. The devised method relies on the definition of a proper acquisition system and on the development of image processing-based routines. Such a system is then implemented on a counting machine is meant to be adopted in the galvanic industrial practice to properly define a suitable set or working parameters (such as current, voltage and deposition time) for the electroplating machine and, thereby, to assure the desired plate thickness from one side and to avoid material waste on the other.

Spike shape and morphometric characteristics are among the key characteristics of cultivated cereals associated with their productivity. Identification of the genes controlling these traits requires morphometric data harvesting and analysis for numerous plants, which is automatable using technologies of digital image analysis. A method for wheat spike morphometry utilizing 2D image analysis is proposed. Digital images are acquired in two variants: a spike on a table (one projection) or fixed with a clip (four projections). The method identifies spike and awns in the image and estimates their quantitative characteristics (area in image, length, width, circularity, etc.). Models of sections, quadrilaterals, and radial model are proposed for describing spike shape. Parameters of these models are used to predict spike shape type (spelt, normal, or compact) by machine learning. The mean error in spike density prediction for the images in one projection is 4.61 (~18%) versus 3.33 (~13%) for the parameters obtained using four projections. F1 measure in automated spike classification into three types is 0.78 using logistic regression (one projection) and 0.85 using random forest method (four projections). The proposed method is implemented in Java; examples of images and user guide are available at http://wheatdb.org/werecognizer.

A lensless camera is an ultra-thin computational-imaging system. Existing lensless cameras are based on the axial arrangement of an image sensor and a coding mask, and therefore, the back side of the image sensor cannot be captured. In this paper, we propose a lensless camera with a novel design that can capture the front and back sides simultaneously. The proposed camera is composed of multiple coded image sensors, which are complementary-metal-oxide-semiconductor~(CMOS) image sensors in which air holes are randomly made at some pixels by drilling processing. When the sensors are placed facing each other, the object-side sensor works as a coding mask and the other works as a sparsified image sensor. The captured image is a sparse coded image, which can be decoded computationally by using compressive-sensing-based image reconstruction. We verified the feasibility of the proposed lensless camera by simulations and experiments. The proposed thin lensless camera realizes super field-of-view imaging without lenses or coding masks, and therefore can be used for rich information sensing in confined spaces. This work also suggests a new direction in the design of CMOS image sensors in the era of computational imaging.

Edge detection is one of the key issues in the field of computer vision and remote sensing image analysis. Although many different edge-detection methods have been proposed for gray-scale, color, and multispectral images, they still face difficulties when extracting edge features from hyperspectral images (HSIs) that contain a large number of bands with very narrow gap in the spectral domain. Inspired by the clustering characteristic of the gravitation, a novel edge-detection algorithm for HSIs is presented in this paper. In the proposed method, we first construct a joint feature space by combining the spatial and spectral features. Each pixel of HSI is assumed to be a celestial object in the joint feature space, which exerts gravitational force to each of its neighboring pixel. Accordingly, each object travels in the joint feature space until it reaches a stable equilibrium. At the equilibrium, the image is smoothed and the edges are enhanced, where the edge pixels can be easily distinguished by calculating the gravitational potential energy. The proposed edge-detection method is tested on several benchmark HSIs and the obtained results were compared with those of three state-of-the-art approaches. The experimental results confirm the efficacy of the proposed method

Machine learning and computer vision have proven to be valuable tools for farmers to streamline their resource utilization to lead to more sustainable and efficient agricultural production. These techniques have been applied to strawberry cultivation in the past with limited success. To build on this past work, in this study two separate sets of strawberry images, along with their associated diseases, were collected and subjected to, resizing, and augmentation. Subsequently, a combined dataset consisting of 9 classes was utilized to fine-tune three distinct pre-trained models: Vision Transformer (ViT), MobileNetV2, and ResNet18. To address the imbalanced class distribution in the dataset, each class was assigned weights to ensure nearly equal impact during the training process. To enhance the outcomes, new images were generated by removing backgrounds, reducing noise, and flipping them. The performances of ViT, MobileNetV2, and ResNet18 were compared after being selected. Customization specific to the task was applied to all three algorithms, and their performances were assessed. Throughout this experiment, none of the layers were frozen, ensuring all layers remained active during training. Attention heads were incorporated into the first 5 and last 5 layers of MobileNetV2 and ResNet18, while the architecture of ViT was modified. The results indicated accuracy factors of 98.4%, 98.1%, and 97.9% for ViT, MobileNetV2, and ResNet18, respectively. Despite the data being imbalanced, the precision, which indicates the proportion of correctly identified positive instances among all predicted positive instances, approached nearly 99% with the ViT. MobileNetV2 and ResNet18 demonstrated similar results. Overall, the analysis revealed that the Vision Transformer model exhibited superior performance in strawberry ripeness and disease classification. The inclusion of attention heads in the early layers of ResNet18 and MobileNet18, along with the inherent attention mechanism in ViT, improved the accuracy of image identification. These findings offer the potential for farmers to enhance strawberry cultivation through passive camera monitoring alone, promoting the health and well-being of the population.

Purpose: This study investigates the impact of different intensity normalization (IN) methods on the overall survival (OS) radiomics models’ performance of MR sequences in primary (pHGG) and recurrent high-grade glioma (rHGG). Methods: MR scans acquired before radiotherapy were retrieved from two independent cohorts (rHGG C1: 197, pHGG C2: 141) from multiple scanners (15, 14). The sequences are T1 weighted (w), contrast-enhanced T1w (T1wce), T2w, and T2w-FLAIR. Sequence-specific significant features (SF) associated with OS, extracted from the tumour volume, were derived after applying 15 different IN methods. Survival analyses were conducted using Cox proportional hazard (CPH) and Poisson regression (POI) models. A ranking score was assigned based on the 10-fold cross-validated (CV) concordance index (C-I), mean square error (MSE), and the Akaike information criterion (AICs), to evaluate the methods’ performance. Results: Scatter plots of the 10-CV C-I and MSE against the AIC showed an impact on the survival predictions between the IN methods and MR sequences (C1/C2 C-I range: 0.62-0.71/0.61-0.72, MSE range: 0.20-0.42/0.13-0.22). White stripe showed stable results for T1wce (C1/C2 C-I: 0.71/0.65, MSE: 0.21/0.14). Combat (0.68/0.62, 0.22/0.15) and histogram matching (HM, 0.67/0.64, 0.22/0.15) showed consistent prediction results for T2w models. They were also the top-performing methods for T1w in C2 (Combat: 0.67, 0.13; HM: 0.67, 0.13), however, only HM achieved high predictions in C1 (0.66, 0.22). After eliminating IN impacted SF using Spearman’s rank-order correlation coefficient, a mean decrease in the C-I and MSE of 0.05 and 0.03 was observed in all four sequences. Conclusion: The IN method impacted the predictive power of survival models. Thus, performance is sequence-dependent.

In this article, we introduce a new approach to human movement by defining the movement as a static object or a super object in one two-dimensional image. This method can allow researchers to label and describe the total movement as an object isolated from a reference video. This ap-proach allows us to perform various tasks, including finding similar movements in a video, measuring, and comparing movements, generating new similar movements, and defining chore-ography by controlling specific parameters in the human body skeleton. As a result of the pre-sented approach, we can eliminate the need to label images manually, disregard the problem of finding the beginning and the end of a movement, overcome synchronization issues between movements, and perform any deep learning network-based operation that processes super objects in images in general. As part of this article, we will demonstrate two application use cases: one il-lustrates how to verify and score a requested movement. In contrast, the other illustrates how to generate similar movements in the human skeleton space by addressing the challenge of supply-ing sufficient training data for deep learning applications (DL). A Variational Auto Encoder (VAE) simulator and an EfficientNet-B7 classifier architecture embedded within a Siamese twin neural network are presented in this paper in order to demonstrate two use cases. These use cases demonstrated the versatility of our innovative concept in measuring, categorizing, inferring hu-man behavior, and generating gestures for other researchers.

Blind image quality assessment (BIQA) aims to evaluate image quality in a way that closely matches human perception. To achieve this goal, the strengths of deep learning and the characteristics of human visual system (HVS) can be combined. In this paper, inspired by the ventral pathway and dorsal pathway of HVS, a dual-pathway convolutional neural network is proposed for BIQA task. The proposed method consists of two pathways: “what” pathway, which mimics the ventral pathway of HVS to extract the content features of distorted images, and the “where” pathway, which mimics the dorsal pathway of HVS to extract the global shape features of distorted images. Then, the features from the two pathways are fused and mapped to an image quality score. Additionally, the gradient images weighted by the contrast sensitivity are used as the input to the “where” pathway, allowing it to extract global shape features that are more sensitive to human perception. Moreover, a dual-pathway multi-scale feature fusion module is designed to fuse the multi-scale features of the two pathways, enabling the model to capture both global features and local details, thus improving the overall performance of the model. The experiments conducted on six databases show that the proposed method achieves the state-of-the-art performance.

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.

The purpose of this work is to compare two fracture prediction models with real-world data. The pure Artificial Neural Network (ANN) model emphasizes regression analysis, while the hybrid model (SVM-ANN) focuses on the combination of regression and classification analysis or Support Vector Machine. The results were subsequently tested against logging data by combining the Machine Learning approach with advanced logging tools. In this context, we used electrical image logs and the dipole acoustic tool which together allowed the distinction of 404 open fractures and 231 closed fractures and, consequently the estimation of fracture porosity. The results are then fed into two machine-learning algorithms. Pure Artificial Neural Networks and hybrid models are used to establish comprehensive results, which are subsequently tested to check the accuracy of the models. The outputs obtained from the two methods demonstrate that the hybridized model has a lower Root Mean Square Error (RMSE) than pure ANN. The results of our approach strongly suggest that incorporating hybridized machine learning algorithms in fracture porosity estimations can contribute to the development of more trustworthy static reservoir models in simulation programs. Finally, the combination of Machine Learning (ML) and well-log analysis do permit reliable estimation of fracture porosity in the Ahnet field in Algeria, where, in many places, advanced logging data is absent and costly.

(1) Background: OCT imaging has been used to assess enamel demineralization in dental research but is not yet developed enough to qualify as a diagnostic technique in clinics. The current capabilities of most commercial acquisition software allow for visual and qualitative assessment. There is a need for a fast and verified batch-processing algorithm for segmenting and analyzing the de-mineralized enamel. This study suggests a GUI MATLAB algorithm for processing and quantitative analysis of the demineralized enamel. (2) Methods: A group of artificially demineralized human enamels was in vitro scanned under the OCT, and ROI frames were extracted. By using a selected intensity threshold colormap, inter- (Ie) and intra- (Ia) prismatic demineralization can be segmented. A set of quantitative measurements for average demineralized depth, average line profile, and integrated reflectivity can be obtained for an accurate assessment. Real and simulated OCT frames were used for algorithm verification. (3) Results: A strong correlation between automated and known Excel measurements for the average demineralization depth was found (R² > 0.97). (4) Conclusions: OCT image segmentation and quantification of the enamel demoralization zones are possible. The algorithm can assess the future development of a real-time assessment of dental diagnostics using an oral probe OCT.

This study aimed to investigate the relationship between weight-bias internalization and eat-ing-disorder psychopathology in treatment-seeking patients with severe obesity using a network approach. Two thousand, one hundred and thirteen patients with obesity consecutively admitted to a specialist clinical unit for obesity were recruited from January 2016 to February 2023. Body mass index was measured, and each patient completed the Weight Bias Internalization Scale (WBSI) and the Eating Disorder Examination Interview (EDE). Network analysis showed that the most central and highly interconnected nodes in the network were related to the EDE items exposure avoidance, dissatisfaction with shape, and wanting an empty stomach. Bridge nodes were found, but the bootstrap difference test on expected bridge influence indicated non-significant centrality differences. Nevertheless, the eating-disorder psychopathology and weight-bias internalization network structure in patients seeking treatment for obesity indicate the prominent role of body dissatisfaction and control of eating and weight in these psychological constructs. This finding, if replicated, could pave the way for a new understanding of the psychological mechanisms operating in patients with obesity.

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.

The reuse of recycled crushed concrete aggregate (RCCA) and reclaimed asphalt pavement (RAP) can provide a sustainable solution for the disposal of C&D materials instead of sending it to landfill. More importantly, it will save energy and reduce impact on the environment. Several states in USA are using RCCA and RAP as base materials for years, focusing on the quality of the recycled materials. The structure of Recycled Aggregate (RA) is more complex than Natural Aggregate (NA). RAs have old mortar adhered on them that forms a porous surface at interfacial transition Zone (ITZ) and prevents new cement mix from bonding strongly with the aggregates. The objective of this work was to correlate microstructural properties like micro-porosity, inter and intra aggregate pores with the unconfined compressive strength (UCS) of RAP and RCCA molds, mixed at different proportions. In this paper, the quantity of micro-pores and their effect on the strength of mixed materials is used as the basis of microstructural analysis of recycled concrete and reclaimed asphalt. Microstructural properties obtained from the analysis of scanning electron microscope (SEM) images were correlated with unconfined compressive strength. Intra-aggregate and inter-aggregate pores were studied for different ratios of cement treated mixture of RAP and RCCA. The results show that the number of pores in the mixture increases considerably by adding RAP, which eventually causes reduction in unconfined compressive strength. In addition, significant morphological and textural changes of recycled aggregates were observed by SEM image analysis.

Global warming, exacerbated by greenhouse gas emissions from non-green product manufacturing, necessitates a shift towards green production to safeguard ecosystems and finite resources. The United Nations Environment Programme emphasizes the importance of environmental considerations in corporate ESG criteria. Despite the higher costs of designing and manufacturing green products, which deter some companies and lead to greenwashing, efforts persist to promote sustainable goods. This study explores enhancing consumer repurchase intentions for green products through social media marketing, emphasizing green values, environmental concerns, brand image, and involvement. Findings reveal social media's role in boosting these factors, thus encouraging green repurchases. Insights are valuable for green businesses, social media groups, environmental agencies, and future research.

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.

This paper investigates the adaptability of four state-of-the-art Artificial Intelligence (AI) models to the Australian mammographic context through transfer learning, explores the impact of image enhancement on model performance and analyses the relationship between AI outputs and histopathological features for clinical relevance and accuracy assessment. A total of 1712 screening mammograms (n=856 cancer cases and n=856 matched normal cases) were used in this study. The 856 cases with cancer lesions were annotated by two expert radiologists and the level of concordance between their annotations was used to establish image subsets. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of Globally aware Multiple Instance Classifier (GMIC), Global-Local Activation Maps (GLAM), I&H and End2End AI models, both in the pre-trained and transfer learning modes, with and without applying the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm. The four AI models with and without transfer learning in the high-concordance subset outperformed those in the entire dataset. Applying the CLAHE algorithm to mammograms improved the performance of the AI models. In the high-concordance subset with transfer learning and CLAHE algorithm applied, the AUC of the GMIC model was highest (0.912), followed by GLAM model (0.909), I&H (0.893) and End2End (0.875). There were significant differences (P<0.05) in the performances of the four AI models between high-concordance subset and entire dataset. The AI models demonstrated significant differences in malignancy probability concerning different tumour size categories in mammograms. The performance of AI models was affected by several factors such as concordance classification, image enhancement and transfer learning. Mammograms with strong concordance of radiologists’ annotations, applying image enhancement and transfer learning could enhance the accuracy of AI models.

Satellite-based data classification performance remains a challenge for research community in the field of land use/land cover mapping. Here we investigated supervised per-pixel classifications performance under different scenarios, based on single and seasonal multispectral data combi-nations of different sensors (Landsat-8 OLI and Sentinel-2 MSI). In case of Landsat, seasonal spectral indices (EVI and NDMI) were included. A typical Mediterranean watershed with a complex landscape comprised of various forest and wetland ecosystems, crops, artificial surfaces, and lake water was selected to test our approach. All available geospatial data from national databases (Forest Map, LPIS, Natura2000 habitats, cadastral parcels, etc.) are used as ancillary data for clas-sification training and validation. We examined and compared the performance of ML, RF, KNN and SVM classifiers under different scenarios for land use/land cover mapping, according to Copernicus Land Cover (CLC2018) nomenclature. In total, eight land use/land cover classes were identified in Landsat-8 OLI and nine in Sentinel-2a MSI for an acceptable overall accuracy over 85%. A comparison of the overall classification accuracies shows that Sentinel-2a overall accuracy was slightly higher than Landsat-8 (96.68% vs. 93.02%). Respectively, the best-performed algorithm was ML in Sentinel-2 while in Landsat-8 was KNN. However, machine-learning algorithms have similar results regardless the type of sensor. We concluded that best classification performances achieved using seasonal multispectral data. Future research should be oriented towards inte-grating time-series multispectral data of different sensors and geospatial ancillary data for land use/land cover mapping.

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.

Degradation of environment quality is currently the prime cause of the recent occurrence of natural disasters; it also contributes in the increase of the area that is prone to natural disasters. This research is aimed to map the potential of areas around Pesanggrahan river in DKI Jakarta by segmenting the Digital Elevation Model derived from LIDAR data. The objective of this segmentation is to find the watershed lines of the DEM image. Data processing in this research is using LIDAR data which take the ground surface data, which is overlaid with Jakarta river map and subsequently, the data is then segmented the image. The expected result of the research is the flood potential area information, especially along the Pesanggrahan river in South Jakarta.

Chaotic theory is commonly being researched for application in image encryption scheme (IES). In this paper, a novel two-dimensional cross hyperchaotic Sine-modulation-Logistic map (2D-CHSLM) based on the famous Sine and Logistic maps. The hyperchaotic behaviors of 2D-CHSLM is testified with the help of their bifurcation diagrams, trajectory plots, Lyapunov exponents, sample entropy, C0 complexity, permutation entropy and 0-1 test. A new bit-level IES with traditional encryption structure is proposed utilizing 2D-CHSLM. The 2D-CHSLM-IES performs a 2D-CHSLM-based bit-level confusion using zig-zag transform and a 2D-CHSLM-based cross coupled diffusion operations for generating a highly secure cipher-image. Then the simulations and security analyses are further carried out with the help of key space, key sensitivity, histogram, correlation, information entropy, differential attack, noise and data loss attacks, prove that the security of the proposed 2D-CHSLM-IES

Image encryption is increasingly becoming an important area of research in information security and network communications, as digital images are widely used in various applications and are vulnerable to various types of attacks. In this research work, a color image cryptosystem that is based on a 3-layer permutation-substitution network (PSN) is proposed. For every layer, an encryption key and an S-box are generated and utilized. Those are based on a four-dimensional (4D) dynamical Chen system of a fractional-order, the Mersenne Twister, OpenSLL, Rule 30 Cellular Automata and Intel’s MKL. The sequential application of Shannon’s ideas of diffusion and confusion for 3 times guarantees a total distortion of any input plain image, resulting in a totally encrypted one. Apart from the excellent and comparable performance to counterpart algorithms from the literature, showcasing resistance to visual, statistical, entropy, differential, known plaintext and brute-force attacks, the proposed image cryptosystem provides an exceptionally superior performance in 2 aspects: a vast key space of 2^1658 and an average encryption rate of 3.34 Mbps. Furthermore, the proposed image cryptosystem is shown to successfully pass all the tests of the NIST SP 800 suite.

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.

Spectral image analysis has the potential to replace traditional approaches for assessing plant responses to different types of stress including herbicide, through non-destructive and high-throughput screening (HTS). Therefore, this study was conducted to develop a rapid bioassay method using a multi-well plate and spectral image analysis for diagnosis of herbicide activity and mode of action. Crabgrass (Digitaria ciliaris) as a model weed was cultivated in multi-well plates and subsequently treated with 6 herbicides with different modes of action when they reached the 1-leaf stage, using only a quarter of the recommended dose. To detect plant response to herbicides, plant spectral images were acquired after herbicide treatment using RGB, infrared (IR) thermal, and chlorophyll fluorescence (CF) sensors and analyzed for diagnosing herbicide efficacy and mode of action. Principal Component Analysis (PCA) using all spectral data successfully distinguished herbicides and clustered depending on their modes of action. The performed experiments have shown that the multi-well plate assay combined with spectral image analysis can be successfully applied for herbicide bioassay. In addition, the use of spectral image sensors, especially in CF image, would facilitate HTS by enabling rapid observation of herbicide response, as early as 3 hours after herbicide treatment.

Inspired by the forward and the reverse channels from the image-size characterization problem in network information theory, we introduce a functional inequality which unifies both the Brascamp-Lieb inequality and Barthe's inequality, which is a reverse form of the Brascamp-Lieb inequality. For Polish spaces, we prove its equivalent entropic formulation using the Legendre-Fenchel duality theory. Capitalizing on the entropic formulation, we elaborate on a "doubling trick" used by Lieb and Geng-Nair to prove the Gaussian optimality in this inequality for the case of Gaussian reference measures.

Research on early stages of corrosion of steel bars, together with the formation and development of cracks induced in the surrounding concrete and caused by chloride penetration, is relevant in improving the durability of reinforced concrete structures. This paper uses integration of the analytical models examined in the published literature, combined with experimental research in corrosion induced at the concrete/steel interface, in estimating the time-to-crack initiation of reinforced concrete subjected to corrosion. This work studies the influence of the porous network and electric current density on the cracking process at early ages. The experimental campaign was performed by using an accelerated corrosion test on a conventional concrete (CC) and a concrete with silica fume (SFC) by submitting them to a current density of 50μA/cm² and 100μA/cm². Examination performed by scanning electron microscopy (SEM) and energy-dispersive X-ray spectroscopy (EDS) provided both qualitative and quantitative information on the penetration of the rust layer in the surrounding concrete porous network. Strain gauges were used to measure corrosion-induced deformations between steel and concrete matrices, as well as the formation of corrosion-induced cracks. A good correlation between the rate of penetration of the rust products in the surrounding pores and the delay of the cracking pressure in concrete was observed from the experimental results. This phenomenon is incorporated into the analytical model by using a reduction factor, which mainly depends on the pore size of the concrete. The crack width obtained exhibited a significant dependency on electric current density at the beginning of the test, depending mainly on the pore size of the concrete later.

Hyperspectral image and LiDAR image fusion plays a crucial role in remote sensing by capturing spatial relationships and modeling semantic information for accurate classification and recognition. However, existing methods, like Graph Convolutional Networks (GCNs), face challenges in constructing effective graph structures due to variations in local semantic information and limited receptiveness to large-scale contextual structures. To overcome these limitations, we proposed a invariant attribute-driven binary bi-branch classification (IABC) method which is a unified network that combines binary Convolutional Neural Network (CNN) and GCN with invariant attributes. Our approach utilizes a joint detection framework that can simultaneously learn features from small-scale regular regions and large-scale irregular regions, resulting in an enhanced structured representation of HSI and LiDAR images in the spectral-spatial domain. This approach not only improves the accuracy of classification and recognition but also reduces storage requirements and enables real-time decision-making, which is crucial for effectively processing large-scale remote sensing data. Extensive experiments demonstrates the superior performance of our proposed method in hyperspectral image analysis tasks. The combination of CNNs and GCNs allows for accurate modeling of spatial relationships and effective construction of graph structures. Furthermore, the integration of binary quantization enhances computational efficiency, enabling real-time processing of large-scale data. Therefore, our approach presents a promising opportunity for advancing remote sensing applications using deep learning techniques.

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

As governments in various countries and regions issue tourism-friendly policies in the post-pandemic period, the voices for tourism consumption recovery and innovative transformation have attracted great attention. Many scholars, experts and industry professionals in the field of festivals are actively exploring efficient solutions for festival marketing and sustainability. It is worth rethinking tourists’ consumption psychology and perceived image toward exiting festival products as well as the antecedents that affect festival loyalty. The Qingdao International Beer Festival, as one of the most influential festivals in China, was selected as the research case for this study. The main goal of this study was to investigate festival consumption promotion mechanism by proposing a conceptual framework in which the associations from destination familiarity and product familiarity to loyal intentions (re-patronage and recommendation) were examined, with mediators of overall festival image, perceived value and overall satisfaction. Furthermore, the moderating role of visitor involvement in the proposed framework was also adequately demonstrated. The research findings are expected to provide a significant reference for the recovery and competitiveness improvement of the entire festival industry.

The Coronavirus disease (COVID-19) caused by a novel coronavirus, SARS-CoV-2, has been declared as a global pandemic. Due to its infection rate and severity, it has emerged as one of the major global threats of the current generation. To support the current combat against the disease, this research aims to propose a Machine Learning based pipeline to detect the COVID-19 infection using the lung Computed Tomography scan images (CTI). This implemented pipeline consists of a number of sub-procedures ranging from segmenting the COVID-19 infection to classifying the segmented regions. The initial part of the pipeline implements the segmentation of the COVID-19 affected CTI using Social-Group-Optimization and Kapur’s Entropy thresholding, followed by k-means clustering and morphology-based segmentation. The next part of the pipeline implements feature extraction, selection and fusion to classify the infection. PCA based serial fusion technique is used in fusing the features and the fused feature vector is then employed to train, test and validate four different classifiers namely Random Forest, k-Nearest Neighbors (KNN), Support Vector Machine with Radial Basis Function, and Decision Tree. Experimental results using benchmark datasets show a high accuracy (> 91%) for the morphology-based segmentation task and for the classification task the KNN offers the highest accuracy among the compared classifiers (> 87%). However, this should be noted that this method still awaits clinical validation, and therefore should not be used to clinically diagnose the ongoing COVID-19 infection.

In recent years, remote sensing technology has been widely used to predict forest stand parameters. In order to compare the effects of different features of remote sensing images and topographic information on the prediction of forest stand parameters, multivariate stepwise regression analysis method was used to build estimation models for important forest stand parameters by using textural and spectral features as well as topographic information of SPOT-5 satellite images in northeastern Heilongjiang Province in China as independent variables. The study results show that the optimal window to predict forest stand parameters using textural features of SPOT-5 satellite image is 9×9; the ability of textural features was better than that of spectral features in terms of predicting forest stand parameters; with the inclusion of topographic information, the accuracy of prediction of all models was improved, of which elevation has the most significant effect. The highest accuracy was achieved when predicting the stand volume (SV) (R²_adj=0.820), followed by basal area (BA) (R²_adj =0.778), accuracy of both above models exceeded 75%. The results show that models combined use of textural, spectral features and topographic information of SPOT-5 images have a good application prospect in predicting forest stand parameters.

Background/Objectives: The aim of the project is a longitudinal assessment of body image and mental health in scoliosis females pre-, postoperatively and in a follow-up, and implementation (one group-CBT scoliosis sample, CBTSS) or not (second group-control scoliosis sample, CSS) of CBT interventions. A healthy female sample (HFS) was also selected for comparative purposes. Methods. 36 in total AIS patients participated in the 1st and 2nd study phases, whereas 23 were eligible in the follow-up. Regarding HFS, 18 participants were included in the study. The CBT intervention took place pre- and postoperatively, during the patients' stay in hospital. Participants completed the Spinal Appearance Questionnaire (SAQ), Body Esteem Scale (BES) and Strengths and Difficulties Questionnaire-25 (SDQ-25). Body image was also assessed using a virtual reality-based application “Avatar Scoliosis 3D”. Results: The difference between the desired and objective, actual body shape is significant preoperatively both in the CBTSS and CSS at p

Target recognition and fine-grained ship classification in remote sensing face the challenges of high inter-class similarity and sample scarcity. A transfer fusion-based ship image harmonization algorithm is proposed to overcome these challenges. This algorithm designs a feature transfer fusion strategy based on the combination of region aware instantiation and attention mechanism. Implement adversarial learning through image harmony generator and discriminator module to generate realistic remote sensing ship harmony images. Furthermore, the do-main encoder and domain discriminator modules are responsible for extracting feature representations of foreground and background, and further aligning ship foreground with remote sensing ocean background features through feature discrimination. Compared with other advanced image conversion techniques, our algorithm delivers more realistic visuals, improving classification accuracy for six ship types by 3% and twelve types by 2.94%, outperforming Sim2RealNet. Finally, a mixed dataset containing data augmentation and harmonizing samples and real data was proposed for the fine-grained classification task of remote sensing ships. Evaluation experiments were conducted on 8 typical fine-grained classification algorithms, and the accuracy of fine-grained classification for all categories of ships was analyzed. The experimental results show that the mixed dataset proposed in this paper effectively alleviates the long tail problem in real datasets, and the proposed remote sensing ship data augmentation framework performs better than state-of-the-art data augmentation methods in fine-grained ship classification tasks.

Color image binarization plays a pivotal role in image preprocessing work, significantly impacting subsequent tasks, particularly in text recognition. This paper concentrates on Document Image Binarization (DIB), aiming to separate a image into foreground (text) and background (non-text content). Through a thorough analysis of conventional and deep learning-based approaches, we conclude that prevailing DIB methods leverage deep learning technology. Furthermore, we explore the receptive fields pre- and post-network training to underscore the Transformer model's advantages. Subsequently, we introduce a lightweight model based on the U-Net structure, enhanced with the Mobile ViT module to better capture global information features in document images. Given its adeptness at learning both local and global features, our proposed model exhibits superior performance on two standard datasets (DIBCO2012 and DIBCO2017) compared to state-of-the-art methods. Notably, our proposed DIB method presents a straightforward end-to-end model devoid of additional image preprocessing or post-processing. Moreover, its parameter count is less than a quarter of the HIP'23 model, which achives best results on three datasets(DIBCO2012, DIBCO2017 and DIBCO2018). Finally, two sets of ablation experiments were conducted to verify the effectiveness of the proposed binarization model.

In this paper we propose a module that uses features learned by a deep convolutional neural network to infer areas of corrosion and segment pixels to corrosion areas of inspection interest. Our segmentation module is based on eigen tree decomposition and information based decision criteria. To interrogate performance we use several state-of-the-art deep learning architectures and compare to our approach. The results indicate that our method produces better results in terms of accuracy and precision, whilst maintaining good (f-score) significance over the entire dataset.

Background: The variability of the obtained results of manual tests assessing the angle of strabismus depends on the experience, skills, and training of the examiner. The authors hope that the new measuring device will provide a more sensitive and repeatable method for detecting small strabismus angles compared to the gold standard – PCT. The purpose of this article is to present an innovative strabismus angle demonstration device, called Strabiscan, to present automated measurements of eye deviation, and to compare the obtained results of these measurements to the traditional manual method. Methods: In patients with the manifest strabismic disease (n = 30) and a group of healthy subjects (n = 30), a detailed history was taken and routine ophthalmologic examinations were performed, including best-corrected distance visual acuity, assessment of refractive error using an autorefractometer after cycloplegia, biomicroscopic evaluation of the anterior segment of the eye, and evaluation of the eye fundus by indirect ophthalmoscopy. Subsequently, each patient and healthy subjects were subjected to a prismatic cover-uncover test using a manual method, and then the presence of strabismus was detected and its angle assessed using demonstration Strabiscan device. Results: In the control group, using the Strabiscan demonstration device, small-angle latent strabismus ≤3DP was diagnosed in 83% of patients, and >3DP in 13%. In contrast, using the prismatic cover-uncover test, latent strabismus ≤3DP was diagnosed in only 13% of patients, and latent strabismus with an angle >3DP in 13% of patients. No statistically significant differences were noted in the measurements of strabismus angles made by the different methods. Conclusions: The Strabiscan demonstration device allows quick and accurate assessment of the strabismus angle. Compared to the prismatic cover-uncover test, it has a higher sensitivity for detecting low-angle latent strabismus. Measurements with the Strabiscan do not require the presence of additional co-assistants for the test.

To improve the adaptability of aerial reflective opto-mechanical structures to low-temperature environments, an optimized thermal control design is proposed. Firstly, the relationship be-tween conventional heating methods and axial/radial temperature differences of mirrors with different shapes is analyzed. Based on heat transfer analyses, it is pointed out that optimized thermal control design is necessary to ensure the temperature uniformity of the fused silica mirror and take into account the temperature level when working in low temperature environ-ments. A thermal control scheme based on temperature negative feedback variable power zone heating is proposed for the characteristics of aerial electro-optics systems. Using the thermal control scheme at low temperatures ensures that the average temperature of the mirror fluctu-ates slowly and slightly around 20℃. At the same time, the temperature differences within a mirror and between the primary mirror and the secondary mirror can be controlled within 5℃. Thereby, satisfactory image quality is obtained.

(1) Background: This study aimed to explore how prolonged mask use during the COVID-19 pandemic affected appearance anxiety; (2) Methods: It implemented a quantitative–qualitative mixed-research approach based on a convenience sample of young people in Taiwan; (3) Results: A total of 1,118 participants completed the online questionnaire. A total of 49 participants reached the 55-point threshold of Appearance Anxiety Scale. Higher score of appearance anxiety was correlated to higher state anxiety statistically (r = 0.4, p < 0.001). Ten participants were interviewed and qualitative content analysis revealed 5 main themes and 16 subthemes. Three of the main themes were related to the positive effects of wearing masks for pandemic prevention and reducing appearance anxiety: “Wearing masks indicates compliance with the epidemic prevention requirement,” “Wearing masks functions as protection against lack of confidence in appearance,” and “Wearing masks helps mitigate the fear of being judged by others.” The remaining two “Wearing masks shifts attention from appearance to figure” and “Prolonged mask wearing exacerbates the anxiety about taking it off” were related to the impacts of long-term mask use; (4) Conclusions: results enhance understanding of negative emotional experiences and anxiety related to physical appearance.

In the realm of artificial intelligence (AI), generative systems, most notably Midjourney, have tremendous power to generate creative images of buildings and sites of Islamic architectural heritage through text-to-image generation based on the internet. The AI-generated representations have significant potential for architects, specialists, and common users. However, the system has considerable limitations when generating images for some buildings and sites where the representations appear too far from their original represented structures. This research article attempts to answer the question: What are the limitations of using the AI system of Midjourney in producing images similar to the original buildings and sites of the Islamic architectural heritage? The research employs prompt engineering techniques based on historical sources as inputs to examine the accuracy of the output of the AI-generated images of selected examples of structures of the Islamic tradition. It compares the output with the original look by employing direct observation and critical analysis of human intelligence (HI). It categorizes these limitations into four groups: (1) limits of the prompt, (2) limits of fame, (3) limits of regionality and historical styles, and (4) limits of architectural elements and details. It concludes that while Midjourney has great capability to represent high-end AI-generated images inspired by the Islamic tradition, it currently falls short of presenting the actual appearance of some of their original structures.

Artificial intelligence techniques are now widely used in various agricultural applications, including the detection of devastating diseases such as late blight (Phytophthora infestans) and early blight (Alternaria solani) affecting potato (Solanum Tuberorsum L.) crops. In this paper, we present a mobile application for potato crop pest detection based on deep neural networks. The images were taken from the PlantVillage dataset with a batch of 1000 images for each of the three identified classes. An exploratory analysis of the architectures used for early and late blight diagnosis in potatoes was performed, achieving an accuracy of 98.76%, with MobileNetv2. Based on the results obtained, an offline mobile application was implemented, supported on devices with Android 4.1 or later, also featuring an information section on the 27 pests affecting potato crops and a gallery of symptoms. For future work, segmentation techniques will be used to highlight the damaged region in the potato leaf by evaluating its extent and possibly identifying different types of pests affecting the same plant.

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.

Track fasteners play a pivotal role in infrastructure inspection for high-speed rail. Yet, images taken by drones often capture shadows cast by electrical towers flanking the high-speed rail tracks. These shadows can hinder the visibility of the track fasteners, thereby impacting detection efficiency and accuracy considerably. The present paper introduces an end-to-end shadow removal algorithm, rooted in generative adversarial network training. The comprehensive network framework is segmented into three sub-networks: pseudo-mask generation, shadow removal, and result refinement. We have integrated a Fourier convolutional residual module to bolster the feature extraction capability of the generator network. This integration ensures the network retains a global receptive field, even in its more superficial layers. By employing an overall weighted loss function, we enhance the quality of the images produced without shadows. Further, a perceptual loss function has been incorporated to retain the structural information of objects, setting the stage for subsequent defect detection. Our results highlight that Pse-ShadowNet adeptly eradicates fastener shadows while maintaining vital visual features, including object position, structure, texture, edges, and other key visual elements. Consequently, the reconstructed images are detailed and showcase superior image quality.

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.

The study of velocimetry is important for characterizing and comprehending the effects of fluid flow, and the Particle Image Velocimetry (PIV) technique is one of the primary approaches for understanding the velocity vector field in a test section. Commercial PIV systems are expensive, with one of the main cost factors being high-speed camera equipment capable of capturing images at high frames per second (fps), rendering them impractical for many applications. This study proposes an evaluation of utilizing smartphones as image acquisition systems for PIV technique application. An experimental setup inspired by the known angular displacement of synthetic particles is proposed. A stepper motor rotates a plate containing an image of synthetic particles on its surface. The motion of the plate is captured by the smartphone camera, and the images are processed using PIVlab-MatLab® software. The use of two smartphones is assessed, with acquisition rates of either 240 fps or 960 fps and varying angular velocities. The results were satisfactory for velocities up to 0.7 m/s at an acquisition rate of 240 fps and up to 1.8 m/s at 960 fps, validating the use of smartphones as a cost-effective alternative for the PIV technique.

Deep neural networks with powerful auto-optimization tools have been widely applied in various research fields, e.g., NLP and computer vision. However, existing neural network architectures typically are constructed using different inductive biases, e.g., preconceptions, expecting to decrease parameter search space during training, reduce computational cost or introduce expert knowledge in the neural network design. As an alternative, Multilayer Perceptron (MLP) provides much better freedom for exploration, has a lower inductive bias than convolutional neural networks (CNNs), and offers good flexibility in learning complex patterns. Even though, such neural architectures are commonly built in a flat Euclidean space, which is not necessarily the optimal space for any data, and is especially not good for modeling hierarchical correlations. Hyperbolic neural networks (HNNs) have gained attention for their ability to capture hierarchical structures present in complex data types like graphs. Recently, there has been an increasing interest to extend HNNs to computer vision tasks, motivated by the observations that images possess rich hierarchical relations. However, this is generally applied by employing a Euclidean backbone for learning higher-level semantic representations and only incorporating a hyperbolic classifier for classification, which, we argue, does not make full use of the advantage of hyperbolic space. Considering the recovery of the attention-free Multilayer Perceptron(MLP), in this paper, we extend it to non-Euclidean space and propose a novel architecture, named Hyperbolic Res-MLP (HR-MLP), that leverages fully hyperbolic layers to learn feature embeddings and perform image classification in an end-to-end fashion. With the help of the proposed Lorentz cross-patch and cross-channel layers, we can directly perform operations in the hyperbolic domain with fewer parameters, making it faster to train and providing comparatively better performance than its Euclidean counterpart. Experiments on CIFAR10, CIFAR100, and MiniImageNet demonstrate a comparable and superior performance when compared to Euclidean baselines. Our code is available at (https://github.com/Ahmad-Omar-Ahsan/HR-MLP)

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.

Remote sensing imagery is of great significance for policy decisions, especially for disaster assessment and disaster relief. To ensure the privacy and inviolability of personal buildings, the information containing these buildings must be anonymized during the remote sensing mapping process. Traditional processing methods for these targets in remote sensing mapping are mainly based on manual retrieval and image editing tools, which are inefficient. Deep learning provides a new direction for target hiding. Although the image inpainting method based on deep learning is faster than the manual method, the cost of training calculation is a disadvantage. And the element-wise product operation used in the model increases the risk of vanished or exploded gradients. We propose a Residual Attention Target Hiding (RATH) model for remote sensing target hiding based on deep learning. RATH uses residual attention modules to replace gated convolutions, reducing parameters and mitigating gradient issues. The residual attention module preserves gated convolution performance but provides an adjustable kernel size. RATH retains gated convolutions for dynamic feature selection and balances model depth and width. Furthermore, this paper modifies the contextual attention layer by adjusting the fusion process to enlarge the fusion patch size. Finally, we extend the edge-guided function to preserve the original target information and confound viewers. Ablation studies on an open dataset prove RATH’s efficiency for image inpainting and target hiding. RATH achieves state-of-the-art results with lower complexity. And it has the highest similarity for edge-guided target hiding. RATH enables robust, efficient target hiding for privacy protection in remote sensing imagery while balancing performance and complexity. Experiments show RATH's superiority over existing methods in hiding arbitrary-shaped targets.

As one of the main equipment of coal transportation, the belt conveyor with detection system is an important direction for the development of intelligent mine. The occurrences of non-coal foreign objects making contact with belts are common phenomenon in complex production environments and improper human operations. In order to avoid major safety accidents caused by scratches, deviation and breakage of the belt, a foreign object detection method is proposed for belt conveyor in this work. Firstly, a foreign object image dataset is collected and established, and IAT image enhancement module and attention mechanism of CBAM are proposed to enhance image data sample. Moreover, to predict the angle information of foreign objects with large aspect ratios, a rotating decoupling head is designed, and a MO-YOLOX network structure is constructed. Some experiments are carried out with the belt conveyor in the mine intelligent mining equipment laboratory, and the detections of different foreign objects are analyzed. Experimental results show that the accuracy, recall, and mAP50 of the proposed rotating frame foreign object detection method reaches 93.87%, 93.69%, and 93.72%, and the average inference time of foreign object detection is 25 ms.

With the advent of deep learning, significant progress has been made in low-light image enhancement methods. However, deep learning requires enormous paired training data, which is challenging to capture in real-world scenarios.To address this limitation, this paper presents a novel unsupervised low-light image enhancement method, which first introduces the frequency domain features of images in low-light image enhancement tasks. Our work is inspired by imagining a digital image as a spatially varying metaphoric “field of light”, then subjecting the influence of physical processes such as diffraction and coherent detection back onto the original image space via a frequency-domain to spatial-domain transformation (inverse Fourier transform). However, the mathematical model created by this physical process still requires complex manual tuning of the parameters for different scene conditions to achieve the best adjustment. Therefore, we proposed a dual-branch convolution network to estimate pixel-wise and high-order spatial interactions for dynamic range adjustment of the frequency feature of the given low-light image. Guided by the frequency feature from the “field of light” and parameter estimation networks, our method enables dynamic enhancement of low-light images. Extensive experiments have shown that our method performs well compared to state-of-the-art unsupervised, and its performance approximates the level of the state-of-the-art supervised methods qualitatively and quantitatively. At the same time, the light network structure design allows the proposed method to have an extremely fast inference speed(nearly 150 FPS on an NVIDIA 3090 Ti GPU for an image of size 600×400×3 ). Furthermore, the potential benefits of our method to object detection in the dark are discussed.

Fine-grained image classification remains an ongoing challenge in the computer vision field, which is particularly intended to identify objects within sub-categories. It is a difficult task since there is a minimal and substantial intra-class variance. The current methods address the issue by first locating selective regions with Region Proposal Networks (RPN), object localization, or part localization, followed by implementing a CNN Network or SVM classifier to those selective regions. This approach, however, makes the process simple by implementing a single-stage end-to-end feature encoding with a localization method, which leads to improved feature representations of individual tokens/regions by integrating the transformer encoder blocks into the Yolov5 backbone structure. These Transformer Encoder Blocks, with their self-attention mechanism, effectively captured the global dependencies and enabled the model to learn relationships between distant regions. This improved the model ability to understand context and captured long-range spatial relationships in the image. We also replaced the Yolov5 detection heads with three transformer heads at the output for object recognition using the discriminative and informative features maps from transformer encoder blocks. We established the potential of the single stage detector for the fine-grained image recognition task, by achieving state of the art 93.4% accuracy, as well as outperforming the existing Yolov5 model. The effectiveness of our approach is assessed using the Stanford car dataset, which includes 16,185 images of 196 different classes of vehicles with significantly identical visual appearances.

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.

It is widely acknowledged that adolescent females are particularly at risk of low body-esteem. Low body-esteem is associated with poor mental health and other negative outcomes. Interventions to help raise body-image could have considerable impact, especially if the intervention is low-cost, easy to implement and scalable. We investigated the efficacy of an intervention where participnants could chose their own clothes to wear during a Physical Education (PE lesson) on changes in body-esteem. We hypothesized that body-esteem would improve with choice. To show that body-esteem is not a transient construct, we tested its stability when assessed in a test-retest design when completed in a classroom setting, hypothesizing body-esteem would be stable. Participants (N =110; Mage =14.9; SDage = 0.68) females completed a 14-item body-esteem scale 4 times; a) wearing school uniform in an assembly, b) during a PE lesson separated by a 2-week gap. The intervention was implemented where students got a choice of PE kit and could wear their own clothes. Findings indicate that body-esteem was stable in the classroom setting where clothes and context were stable, but improved significantly when participants were given a free choice of kit to wear during PE. We argue that this low-cost and scalable intervention represents a useful start point for helping support low body-esteem among a potentially vulnerable population.

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

Enhancing underwater images in epicontinental sea is a challenging problem owing to the influence of ocean currents, the refraction, absorption and scattering of light by suspended particles, and the weak illumination intensity. Recently, different methods have relied on the underwater image formation model and deep learning techniques to restore the underwater image, but they tend to degrade underwater image, interference of background clutter and miss boundary details of blue regions. Improved image fusion and enhancement algorithm based on a priori dark channel is proposed in this paper. Image edge features sharpening and dark detail enhancement by homomorphism filtering in CIELab color space is realized. In RGB color space, the multi-scale retinal with color restoration (MSRCR) algorithm is used to improve color deviation and enhance color saturation, and the contrast-limited adaptive histogram equalization (CLAHE) algorithm is used to de fog and enhance image contrast. Finally, according to the dark channel images of the three processing results, the final enhanced image is obtained by linear fusion of multiple images and multiple channels. Experimental results demonstrate the effectiveness and practicality of the proposed method on various datasets.

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.

With the continuous development of urbanization and industrialization in the world, concrete is widely used in various engineering constructions as an engineering material. However, the consequent problem of durability of concrete structures is also becoming increasingly prominent. As an important additional measures, protective coating can effectively improve the durability of concrete performance. Moreover, the uniformity of the concrete surface coating will directly affect its protective effect. Therefore, we propose a nondestructive inspection and evaluation method of coating uniformity based on infrared imaging and cluster analysis for concrete surface coating uniformity detection and evaluation. Based on the obtained infrared images, a series of processing and analysis of the images were carried out using MATLAB software to obtain the characteristics of the infrared images of concrete surface. Finally, by extracting the temperature distribution data of the pixel points on the concrete surface, an evaluation method of concrete surface coating uniformity based on a combination of cluster analysis and hierarchical analysis was established. The evaluation results show that the determination results obtained by this method are consistent with the actual situation. This study has a positive contribution to the testing of concrete surface coating uniformity and its evaluation.

The passion of bodybuilding athletes for a symmetric, lean, heavily muscled body leads them to carry out exhausting exercise programs and restrictive eating regimens, sometimes resulting in disordered eating behaviors. This study investigates potential exacerbators on the development of disordered eating in bodybuilding and strength athletes. The study involved 103 Cypriot bodybuilding athletes of both sexes, performing at three levels: professional, recreational and strength athletes. The Eating Attitude Test 26 (EAT-26) and The Three Factor Eating Questionnaire (TFEQ-R21) were used to evaluate disordered eating and eating behaviors respectively. The current study was performed under the auspices of the Hellenic Center of Education & Treatment of Eating Disorders (KEADD). The degree of deviation between the perceived ideal body weight and the actual body weight was associated with increased risk of eating disorder. Athletes who desired a lower body weight recorded higher scores on EAT-26 overall, and the subscales of dieting and bulimia. Cognitive restraint and emotional eating scales of TFEQ-R21 were more pronounced in the non-professional athletes. The emotional eating score was higher in women. There is a need for appropriate sport-specific, gender-specific preventive intervention to deescalate the risk of eating disorder, in both professional and non-professional bodybuilding athletes.

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.

Gwosch et al. (2020) and Balzarotti et al. (2017) purport MINFLUX as the next revolutionary fluorescence microscopy technique claiming a spatial resolution in the range of 1-3 nm in fixed and living cells. Though the claim of molecular resolution is attractive, I am concerned whether true 1 nm resolution has been attained. Here, I compare the performance with other super-resolution methods focussing particularly on spatial resolution claims, atypical image rendering, visualisation enhancement, subjective filtering of localizations, detection vs labelling efficiency and the possible limitations when imaging biological samples containing densely labelled structures. I hope the analysis and evaluation parameters presented here are not only useful for future research directions but also microscope users, developers and core facility managers when deciding on an investment for the next 'state-of-the-art' instrument.

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.

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.

Contrary to optical images, Synthetic Aperture Radar (SAR) images are in different electromagnetic spectrum where the human visual system is not accustomed to. Thus, with more and more SAR applications, the demand for enhanced high-quality SAR images has increased considerably. However, high-quality SAR images entail high costs due to the limitations of current SAR devices and their image processing resources. To improve the quality of SAR images and to reduce the costs of their generation, we propose a Dialectical Generative Adversarial Network (Dialectical GAN) to generate high-quality SAR images. This method is based on the analysis of hierarchical SAR information and the “dialectical” structure of GAN frameworks. As a demonstration, a typical example will be shown where a low-resolution SAR image (e.g., a Sentinel-1 image) with large ground coverage is translated into a high-resolution SAR image (e.g., a TerraSAR-X image). Three traditional algorithms are compared, and a new algorithm is proposed based on a network framework by combining conditional WGAN-GP (Wasserstein Generative Adversarial Network - Gradient Penalty) loss functions and Spatial Gram matrices under the rule of dialectics. Experimental results show that the SAR image translation works very well when we compare the results of our proposed method with the selected traditional methods.

Over the years, artificial intelligence (AI) is spreading its roots in different areas by utilizing the concept of making the computers learn and handle complex tasks that previously require substantial laborious tasks by human beings. With better accuracy and speed, AI is helping lawyers to streamline work processing. New legal AI software tools like Catalyst, Ross intelligence, and Matlab along with natural language processing provide effective quarrel resolution, better legal clearness, and superior admittance to justice and fresh challenges to conventional law firms providing legal services using leveraged cohort correlate model. This paper discusses current applications of legal AI and suggests deep learning and machine learning techniques that can be applied in future to simplify the cumbersome legal tasks.

Dislocation is one of the major challenges in unmanned aerial vehicle (UAV) image stitching. In this paper, we propose a new dynamic programming for seamlessly stitching UAV images using optical flow. Our solution consists of two steps: Firstly, an image-matching algorithm is used to correct the images so that they are in the same coordinate system. Secondly, a new dynamic programming algorithm is develop based on the concept of a stereo dual-channel energy accumulation using optical flow. A new energy aggregation and traversal strategy is adopted in our solution, which can find a more optimal seam line for adjacent image stitching. Our algorithm overcomes the theoretical limitation of the classical Duplaquet algorithm. Experiments show that the algorithm can effectively solve the dislocation problem in UAV image stitching. Beyond that, our solution is also direction-independent, which has more adaptability and robustness for UAV images.

This paper investigates existing mathematical morphology based techniques applied for performing malaria parasites detection and identification in both Giemsa and Leishman stained blood smears images. Malaria is an epidemic health disease and a rapid, accurate diagnosis is necessary for proper intervention. Generally, pathologists visually examine blood stained slides for malaria diagnosis; this kind of visual inspection is subjective, errorprone and time consuming. In order to cope with such issues, computer-aided methods have been increasingly evolved for abnormal erythrocyte and/or parasites detection, segmentation and semi/fully automated classification. The aim of this paper is to present a review of recent mathematical morphology based methods for malaria parasite detection.

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.

The integration of Artificial Intelligence (AI) with Digital Twins (DTs) has emerged as a promising approach to revolutionize healthcare, particularly in the diagnosis and management of thoracic disorders. This study proposes a comprehensive framework, named Lung-DT, which leverages IoT sensors and AI algorithms to establish a digital representation of a patient’s respiratory health. Using the YOLOv8 neural network, the Lung-DT system accurately classifies chest X-Rays into five distinct categories of lung diseases, including "Normal," "Covid," "Lung Opacity," "Pneumonia," and "Tuberculosis". The system’s performance was evaluated on a chest X-Ray dataset, demonstrating an impressive average accuracy of 96.6% across all classes. Further tests (prediction) were conducted on the trained network using a third dataset available in the literature and completely unknown to the network, yielding an average accuracy of 98% across three classes. The proposed Lung-DT framework offers several advantages over conventional diagnostic methods. Firstly, it enables real-time monitoring of lung health through continuous data acquisition from IoT sensors, facilitating early diagnosis and intervention. Secondly, the AI-powered classification module provides automated and objective assessments of chest X-Rays, reducing dependence on subjective human interpretation. Thirdly, the twin digital representation of the patient’s respiratory health allows for comprehensive analysis and correlation of multiple data streams, providing valuable insights for personalized treatment plans. The integration of IoT sensors, AI algorithms, and DT technology within the Lung-DT system demonstrates a significant step towards improving thoracic healthcare. By enabling continuous monitoring, automated diagnosis, and comprehensive data analysis, the Lung-DT framework has enormous potential to enhance patient outcomes, reduce healthcare costs, and optimize resource allocation.