Search

This study investigated the use of deep learning-generated virtual positron emission tomography (PET)-like gated single-photon emission tomography (SPECT VP) for assessing myocardial strain, overcoming limitations of conventional SPECT. SPECT-to-PET translation models for short-axis, horizontal, and vertical long-axis planes were trained using image pairs from the same patients in stress (720 image pairs from 18 patients) and resting states (920 image pairs from 23 patients). Patients without ejection-fraction changes during SPECT and PET were selected for training. We independently analyzed circumferential strains from short-axis-gated SPECT, PET, and model-generated SPECT VP images using a feature-tracking algorithm. Longitudinal strains were similarly measured from horizontal and vertical long-axis images. Intraclass correlation coefficients (ICCs) were calculated with two-way random single-measure SPECT and SPECT VP (PET). ICCs (95% confidence intervals) were defined as excellent (≥ 0.75), good (0.60–0.74), moderate (0.40–0.59), or poor (≤ 0.39). Moderate ICCs were observed for SPECT-derived stressed circumferential strains (0.56 [0.41–0.69]). Excellent ICCs were observed for SPECT VP -derived stressed circumferential strains (0.78 [0.68–0.85]). Excellent ICCs of stressed longitudinal strains from horizontal and vertical long axes, derived from SPECT and SPECT VP , were observed (0.83 [0.73–0.90], 0.91 [0.85–0.94]). Deep-learning SPECT-to-PET transformation improves circumferential strain measurement accuracy using standard-gated SPECT. Furthermore, the possibility of applying longitudinal strain measurements via both PET and SPECT VP was demonstrated. This study provides preliminary evidence that SPECT VP obtained from standard-gated SPECT with postprocessing potentially adds clinical value through PET-equivalent myocardial strain analysis without increasing the patient burden. [ABSTRACT FROM AUTHOR]

To address the challenge of image matching posed by significant modal differences in remote sensing images influenced by snow cover, this paper proposes an innovative image transformation-based matching method. Initially, the Pix2Pix-GAN conversion network is employed to transform remote sensing images with snow cover into images without snow cover, reducing the feature disparity between the images. This conversion facilitates the extraction of more discernible features for matching by transforming the problem from snow-covered to snow-free images. Subsequently, a multi-level feature extraction network is utilized to extract multi-level feature descriptors from the transformed images. Keypoints are derived from these descriptors, enabling effective feature matching. Finally, the matching results are mapped back onto the original snow-covered remote sensing images. The proposed method was compared to well-established techniques such as SIFT, RIFT2, R2D2, and ReDFeat and demonstrated outstanding performance. In terms of NCM, MP, Rep, Recall, and F1-measure, our method outperformed the state of the art by 177, 0.29, 0.22, 0.21, and 0.25, respectively. In addition, the algorithm shows robustness over a range of image rotation angles from −40° to 40°. This innovative approach offers a new perspective on the task of matching multi-temporal snow-covered remote sensing images. [ABSTRACT FROM AUTHOR]

Deep Neural Networks (DNNs) exhibit vulnerability to specially designed adversarial examples and are prone to deception. Although current detection techniques can identify some malicious inputs, their protective capabilities remain insufficient when confronted with complex attacks. This paper proposes a novel unsupervised adversarial example detection method based on unlabeled data. The core idea is to transform the adversarial example detection problem into an anomaly detection problem through feature construction and fusion. To this end, five core components are designed, including image transformation, neural network classifier, heatmap generation, distance calculation, and anomaly detector. Firstly, the original images are transformed, and the images before and after the transformation are input into the neural network classifier. The prediction probability array and convolutional layer features are extracted to generate a heatmap. The detector is extended from focusing solely on the model's output layer to the input layer features, enhancing its ability to model and measure the disparities between adversarial and normal samples. Subsequently, the KL divergence of the probability arrays and the change distance of the heatmap focus points of the images before and after the transformation are calculated, and the distance features are then input into the anomaly detector to determine whether the example is adversarial. Experiments on the large-scale, high-quality image dataset ImageNet show that our detector achieves an average AUC (Area Under the ROC Curve) value of 0. 77 against five different types of attacks, demonstrating robust detection performance. Compared with other cutting edge unsupervised adversarial example detectors, our detector has a drastically enhanced TPR (True Positive Rate) while maintaining a comparable false alarm rate, indicating its significant advantage in detection capability. [ABSTRACT FROM AUTHOR]

To address the challenge of image matching posed by significant modal differences in remote sensing images influenced by snow cover, this paper proposes an innovative image transformation-based matching method. Initially, the Pix2Pix-GAN conversion network is employed to transform remote sensing images with snow cover into images without snow cover, reducing the feature disparity between the images. This conversion facilitates the extraction of more discernible features for matching by transforming the problem from snow-covered to snow-free images. Subsequently, a multi-level feature extraction network is utilized to extract multi-level feature descriptors from the transformed images. Keypoints are derived from these descriptors, enabling effective feature matching. Finally, the matching results are mapped back onto the original snow-covered remote sensing images. The proposed method was compared to well-established techniques such as SIFT, RIFT2, R2D2, and ReDFeat and demonstrated outstanding performance. In terms of NCM, MP, Rep, Recall, and F1-measure, our method outperformed the state of the art by 177, 0.29, 0.22, 0.21, and 0.25, respectively. In addition, the algorithm shows robustness over a range of image rotation angles from −40° to 40°. This innovative approach offers a new perspective on the task of matching multi-temporal snow-covered remote sensing images.

Artistic image transformation is a computer technique widely applied in art creation, design, entertainment, and cultural heritage by converting images into artistic styles. It offers innovative ways for artists to express themselves, provides designers with more choices and inspiration, enhances visual esthetics, and enables creative implementations in movies, games, and virtual reality. Additionally, it aids in the restoration and preservation of ancient artworks, allowing a deeper appreciation of classical art. Traditional image transformation methods, though effective for simple effects, lack the flexibility and expressiveness of deep learning–based approaches. To enhance the effectiveness and efficiency of artistic image transformation, this paper employs generative adversarial networks (GANs), which utilize an adversarial training mechanism between a generator and a discriminator to produce high‐quality and realistic image transformations. This study introduces spectral normalization (SNGAN) to further improve GAN performance by constraining the spectral norm of the discriminator's weight matrix, preventing gradient issues during training, thus improving convergence and image quality. Experimental results on the CHAOS dataset indicate that the proposed SNGAN model achieves the lowest mean absolute error (MAE) of 0.3420, the highest peak signal‐to‐noise ratio (PSNR) of 32.1423, and a structural similarity index (SSIM) of 0.6696, closely matching the best result. Additionally, the SNGAN model demonstrates the shortest training time, highlighting its efficiency. These results confirm that the proposed method achieves more realistic and efficient artistic image transformations compared to traditional methods and other deep learning algorithms. [ABSTRACT FROM AUTHOR]

Lens phenomena, such as caustics, image distortions, and the formation of multiple images, are commonly observed in various refracting geometries, including raindrops, drinking glasses, and transparent vases. In this study, we investigate the ball lens as a representative example to showcase the capabilities of Berry's eye caustic as an optical tool. Unlike the conventional paraxial approximation, the eye caustic enables a comprehensive understanding of image transformations throughout the entire optical space. Through experimental exploration, we establish the relationship between the eye caustic and traditional light caustics. Furthermore, we provide mathematical expressions to describe both the caustic and the image transformations that occur when viewing objects through the ball lens. This approach could be of interest for optics education, as it addresses two fundamental challenges in image formation: overcoming the limitations of the paraxial approximation and recognizing the essential role of the observer in comprehending lens phenomena. [ABSTRACT FROM AUTHOR]

Visual In-Context Learning (ICL) has emerged as a promising research area due to its capability to accomplish various tasks with limited example pairs through analogical reasoning. However, training-based visual ICL has limitations in its ability to generalize to unseen tasks and requires the collection of a diverse task dataset. On the other hand, existing methods in the inference-based visual ICL category solely rely on textual prompts, which fail to capture fine-grained contextual information from given examples and can be time-consuming when converting from images to text prompts. To address these challenges, we propose Analogist, a novel inference-based visual ICL approach that exploits both visual and textual prompting techniques using a text-to-image diffusion model pretrained for image inpainting. For visual prompting, we propose a self-attention cloning (SAC) method to guide the fine-grained structural-level analogy between image examples. For textual prompting, we leverage GPT-4V's visual reasoning capability to efficiently generate text prompts and introduce a cross-attention masking (CAM) operation to enhance the accuracy of semantic-level analogy guided by text prompts. Our method is out-of-the-box and does not require fine-tuning or optimization. It is also generic and flexible, enabling a wide range of visual tasks to be performed in an in-context manner. Extensive experiments demonstrate the superiority of our method over existing approaches, both qualitatively and quantitatively. Our project webpage is available at https://analogist2d.github.io. [ABSTRACT FROM AUTHOR]

Recently, deep learning methods are often used in wafer map failure pattern classification. CNN requires less feature engineering but still needs preprocessing, e.g., denoising and resizing. Denoising is used to improve the quality of the input data, and resizing is used to transform the input into an identical size when the input data sizes are various. However, denoising and resizing may distort the original data information. Nevertheless, CNN-based applications are focusing on studying different feature map architectures and the input data manipulation is less attractive. In this study, we proposed an image hash layer triggered CNN framework for wafer map failure pattern retrieval and classification. The motivation and novelty are to design a CNN layer that can play as a resizing, information retrieval-preservation method in one step. The experiments proved that the proposed hash layer can retrieve the failure pattern information while maintaining the classification performance even though the input data size is decreased significantly. In the meantime, it can prevent overfitting, false negatives, and false positives, and save computing costs to a certain extent. [ABSTRACT FROM AUTHOR]

The subject matter of this article involves reviewing and developing methods for the comparison and transformation of images obtained using UAV via Computer Vision tools. The goal is to improve methods for image comparison and transformation. Various image-processing methods were employed to achieve the goal of this study,thereby contributing to the development of practical algorithms and approaches for image analysis and comparison. The tasks can be described as follows: 1) development of image comparison methods: design tools for the comparison of images from UAV that efficiently detect differences using algorithms such as cv2.absdiff and the PIL module; 2) Image transformation: implement transformation methods for images from UAV, including perspective transformation and thresholding, to enhance the quality and accuracy of image analysis. The methods used were algorithm development, image transformation methods, statistical analysis, experimental testing, and performance evaluation. The metrics used in this article are response time and accuracy. Algorithms for image comparison have also been refined, particularly those transformed through Global Threshold Value, Adaptive Mean Thresholding, and Adaptive Gaussian Thresholding. A novel change filtering method was introduced to enhance the precision of image comparison by filtering out insignificant alterations following image transformation. Comprehensive investigation of image comparison involving edge detection methods has been systematically presented. The results contain the development of practical algorithms and approaches for image analysis and comparison applicable in diverse areas such as military, security, and agriculture. Possibilities of applying our methods and algorithms in the context of drones were also considered, which is particularly relevant in tasks related to computer vision in unmanned aerial vehicles, where limited resources and the need for real-time processing of a large volume of data create unique challenges. Conclusions. The results contain OpenCV and PIL image comparison methods. OpenCV pixel-by-pixel comparison algorithm showed a better response time with the same accuracy. OpenCV method has 92,46% response time improvement compared with PIL and is 276ms. As for image thresholding with comparison, a method based on Global Threshold Value showed the shortest response time (266ms) and the lowest accuracy. The highest accuracy and response time (366ms) were obtained using the Adaptive Gaussian Thresholding method.

This paper addresses the critical issue of fault detection and prediction in electric motor machinery, a prevalent challenge in industrial applications. Faults in these machines, stemming from mechanical or electrical issues, often lead to performance degradation or malfunctions, manifesting as abnormal signals in vibrations or currents. Our research focuses on enhancing the accuracy of fault classification in electric motor facilities, employing innovative image transformation methods—recurrence plots (RPs), the Gramian angular summation field (GASF), and the Gramian angular difference field (GADF)—in conjunction with a multi-input convolutional neural network (CNN) model. We conducted comprehensive experiments using datasets encompassing four types of machinery components: bearings, belts, shafts, and rotors. The results reveal that our multi-input CNN model exhibits exceptional performance in fault classification across all machinery types, significantly outperforming traditional single-input models. This study not only demonstrates the efficacy of advanced image transformation techniques in fault detection but also underscores the potential of multi-input CNN models in industrial fault diagnosis, paving the way for more reliable and efficient monitoring of electric motor machinery. [ABSTRACT FROM AUTHOR]

Data augmentation involves artificially expanding a dataset by applying various transformations to the existing data. Recent developments in deep learning have advanced data augmentation, enabling more complex transformations. Especially vital in the medical domain, deep learning-based data augmentation improves model robustness by generating realistic variations in medical images, enhancing diagnostic and predictive task performance. Therefore, to assist researchers and experts in their pursuits, there is a need for an extensive and informative study that covers the latest advancements in the growing domain of deep learning-based data augmentation in medical imaging. There is a gap in the literature regarding recent advancements in deep learning-based data augmentation. This study explores the diverse applications of data augmentation in medical imaging and analyzes recent research in these areas to address this gap. The study also explores popular datasets and evaluation metrics to improve understanding. Subsequently, the study provides a short discussion of conventional data augmentation techniques along with a detailed discussion on applying deep learning algorithms in data augmentation. The study further analyzes the results and experimental details from recent state-of-the-art research to understand the advancements and progress of deep learning-based data augmentation in medical imaging. Finally, the study discusses various challenges and proposes future research directions to address these concerns. This systematic review offers a thorough overview of deep learning-based data augmentation in medical imaging, covering application domains, models, results analysis, challenges, and research directions. It provides a valuable resource for multidisciplinary studies and researchers making decisions based on recent analytics.

The existing classification of time-series data has difficulties that traditional methodologies struggle to address, such as complexity and dynamic variation. Difficulty with pattern recognition and long-term dependency modeling, high dimensionality and complex interactions between variables, and incompleteness of irregular intervals, missing values, and noise are the main causes for the degradation of model performance. Therefore, it is necessary to develop new classification methodologies to effectively process time-series data and make real-world applications. Accordingly, this study proposes ViT-based multi-scale classification using digital signal processing and image transformation. It comprises feature extraction through digital signal processing (DSP), image transformation, and vision transformer (ViT) based classification. In the DSP stage, a total of five features are extracted through sampling, quantization, and discrete fourier transform (DFT), which are sampling time, sampled signal, quantized signal, and magnitudes and phases extracted through DFT processing. Subsequently, the extracted multi-scale features are used to generate new images. Finally, based on the generated images, a ViT model is applied to make multi-class classification. This study confirms the superiority of the proposed approach by comparing traditional models with ViT and convolutional neural network (CNN) models. Particularly, by showing excellent classification performance even for the most challenging classes, it proves effective data processing in terms of data diversity. Ultimately, this study suggests a methodology for the analysis and classification of time-series data and shows that it has the potential to be applied to a wide range of data analysis problems.

The automation of systems and the accelerated digital transformations across various industries have rendered the manual monitoring of systems difficult. Therefore, the automatic detection of system anomalies is essential in diverse industries. Various deep learning-based techniques have been developed for anomaly detection in multivariate time-series data with promising performance. However, there are several challenges: 1) difficulty in understanding the relationships among time-series data due to their complexity and high-dimensionality, 2) limitation in distinguishing anomalies from normal data that exhibit similar distributional patterns, and 3) lack of intuitive interpretation of anomaly detection results. To address these issues, we propose a novel approach referred to as the time-series to image-transformed adversarial autoencoder (T2IAE), which adopts image transformation techniques and convolutional neural network (CNN)-based adversarial learning. Image transformation techniques were used to effectively capture the local features of adjacent time points. Two CNN-based adversarial autoencoders competitively learned to distinguish between normal and abnormal data. We experimentally analyzed five real-world multivariate time-series datasets, wherein the proposed model achieved superior anomaly detection performance compared with state-of-the-art methods. Moreover, the proposed model enables humans to intuitively interpret the detection results, facilitating appropriate explanations of the results and enhancing the model’s usability.

Tables are commonly used for effective and compact representation of relational information across the data in diverse document classes like scientific papers, financial statements, newspaper articles, invoices, or product descriptions. However, table structure detection is a relatively simple process for humans, but recognizing precise table structure is still a computer vision challenge. Further, innumerable possible table layouts increase the risk of automatic topic modeling and understanding the capability of each table from the generic document. This paper develops the framework to recognize the table structure from the Compound Document Image(CDI). Initially, the bilateral filter is designed for image transformation, enhancing CDI quality. An improved binarization-Sauvola algorithm (IBSA) is proposed to degrade the tables with uneven illumination, low contrast, and uniform background. The morphological Thinning method extracts the line from the table. The masking approach extracts the row and column from the table. Finally, the ResNet Attention model optimized over Black Widow optimization-based mutual exclusion (BWME) is developed to recognize the table structure from the document images. The UNLV, TableBank, and ICDAR-2013 table competition datasets are used to evaluate the proposed framework's performance. Precision and accuracy are the metrics considered for evaluating the proposed framework performance. From the experimental results, the proposed framework achieved a precision value of 96.62 and the accuracy value of 94.34, which shows the effectiveness of the proposed approach's performance. [ABSTRACT FROM AUTHOR]

Permanent magnets (PMs) provide high efficiency for synchronous motors used for driving drilling tools. Demagnetization is a special fault that reduces the efficiency of the permanent magnet synchronous motor (PMSM) and thus affects the performance of the drilling tools. Therefore, early detection of demagnetization is important for safe and efficient operation. However, it is difficult to detect multiple demagnetization types at the same time using traditional fault diagnosis methods, and the recognition accuracy cannot be guaranteed. To solve the above problem, this article proposes a method combining Gramian angular field (GAF) transform and convolutional neural network (CNN) to recognize and classify different types of demagnetization faults based on output torque signal. Firstly, the thermal demagnetization model of PM was obtained by experiments, and the finite element model (FEM) of PMSM for electric drilling tools was established to analyze the torque, back electromotive force (BEMF), and air gap flux density under different demagnetization faults. Then, the acquired one-dimensional torque signals were transformed into two-dimensional gray images based on the GAF method to enhance the fault features. To improve the generalization ability of the CNN, these gray images were augmented through increasing noise. Finally, the CNN structure was designed and trained with a training accuracy of 98.33%, and the effectiveness of the method was verified by the demagnetization fault experiment. The results show that the testing accuracy of the CNN model was 97.41%, indicating the proposed method can diagnose various demagnetization faults effectively, and that it is immune to loads. [ABSTRACT FROM AUTHOR]

The subject matter of this article involves reviewing and developing methods for the comparison and transformation of images obtained using UAV via Computer Vision tools. The goal is to improve methods for image comparison and transformation. Various image-processing methods were employed to achieve the goal of this study, thereby contributing to the development of practical algorithms and approaches for image analysis and comparison. The tasks can be described as follows: 1) development of image comparison methods: design tools for the comparison of images from UAV that efficiently detect differences using algorithms such as cv2.absdiff and the PIL module; 2) Image transformation: implement transformation methods for images from UAV, including perspective transformation and thresholding, to enhance the quality and accuracy of image analysis. The methods used were algorithm development, image transformation methods, statistical analysis, experimental testing, and performance evaluation. The metrics used in this article are response time and accuracy. Algorithms for image comparison have also been refined, particularly those transformed through Global Threshold Value, Adaptive Mean Thresholding, and Adaptive Gaussian Thresholding. A novel change filtering method was introduced to enhance the precision of image comparison by filtering out insignificant alterations following image transformation. Comprehensive investigation of image comparison involving edge detection methods has been systematically presented. The results contain the development of practical algorithms and approaches for image analysis and comparison applicable in diverse areas such as military, security, and agriculture. Possibilities of applying our methods and algorithms in the context of drones were also considered, which is particularly relevant in tasks related to computer vision in unmanned aerial vehicles, where limited resources and the need for real-time processing of a large volume of data create unique challenges. Conclusions. The results contain OpenCV and PIL image comparison methods. OpenCV pixel-by-pixel comparison algorithm showed a better response time with the same accuracy. OpenCV method has 92,46% response time improvement compared with PIL and is 276ms. As for image thresholding with comparison, a method based on Global Threshold Value showed the shortest response time (266ms) and the lowest accuracy. The highest accuracy and response time (366ms) were obtained using the Adaptive Gaussian Thresholding method. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have significantly contributed to recent advances in machine learning and computer vision. Although initially designed for image classification, the application of CNNs has stretched far beyond the context of images alone. Some exciting applications, e.g., in natural language processing and image segmentation, implement one-dimensional CNNs, often after a pre-processing step that transforms higher-dimensional input into a suitable data format for the networks. However, local correlations within data can diminish or vanish when one converts higher-dimensional data into a one-dimensional string. The Hilbert space-filling curve can minimize this loss of locality. Here, we study this claim rigorously by comparing an analytical model that quantifies locality preservation with the performance of several neural networks trained with and without Hilbert mappings. We find that Hilbert mappings offer a consistent advantage over the traditional flatten transformation in test accuracy and training speed. The results also depend on the chosen kernel size, agreeing with our analytical model. Our findings quantify the importance of locality preservation when transforming data before training a one-dimensional CNN and show that the Hilbert space-filling curve is a preferential transformation to achieve this goal. [ABSTRACT FROM AUTHOR]

Image obfuscation techniques (e.g., pixelation, blurring and masking,...) have been developed to protect sensitive information in images (e.g. individuals' faces). In a previous work, we designed a recommendation framework that evaluates the robustness of image obfuscation techniques and recommends the most resilient obfuscation against Deep-Learning assisted attacks. In this paper, we extend the framework due to two main reasons. First, to the best of our knowledge there is not a standardized evaluation methodology nor a defined model for adversaries when evaluating the robustness of image obfuscation and more specifically face obfuscation techniques. Therefore, we adapt a three-components adversary model (goal, knowledge and capabilities) to our application domain (i.e., facial features obfuscations) and embed it in our framework. Second, considering several attacking scenarios is vital when evaluating the robustness of image obfuscation techniques. Hence, we define three threat levels and explore new aspects of an adversary and its capabilities by extending the background knowledge to include the obfuscation technique along with its hyper-parameters and the identities of the target individuals. We conduct three sets of experiments on a publicly available celebrity faces dataset. Throughout the first experiment, we implement and evaluate the recommendation framework by considering four adversaries attacking obfuscation techniques (e.g. pixelating, Gaussian/motion blur and masking) via restoration-based attacks. Throughout the second and third experiments, we demonstrate how the adversary's attacking capabilities (recognition-based and Restoration & Recognition-based attacks) scale with its background knowledge and how it increases the potential risk of breaching the identities of blurred faces. [ABSTRACT FROM AUTHOR]

Convolutional neural networks have achieved great success in computer vision, but incorrect predictions would be output when applying intended perturbations on original input. These human-indistinguishable replicas are called adversarial examples, which on this feature can be used to evaluate network robustness and security. White-box attack success rate is considerable, when already knowing network structure and parameters. But in a black-box attack, the adversarial examples success rate is relatively low and the transferability remains to be improved. This article refers to model augmentation which is derived from data augmentation in training generalizable neural networks, and proposes resizing invariance method. The proposed method introduces improved resizing transformation to achieve model augmentation. In addition, ensemble models are used to generate more transferable adversarial examples. Extensive experiments verify the better performance of this method in comparison to other baseline methods including the original model augmentation method, and the black-box attack success rate is improved on both the normal models and defense models. [ABSTRACT FROM AUTHOR]

Nowadays image morphing has become one of the important techniques in applications that require a graphical representation of objects. Morphing tools have become very well known among users who work on multimedia applications such as art effects, virtual games, photo morphing, and social media, in addition to scientific and academic fields. There are many algorithms to apply morphing operations, including the basic and improved techniques, which share some essential stages, but vary in the algorithm details and the produced image qualities. Morphing techniques, in general, are based on image features and changing them through a warping process to produce another image or mixing two images to produce a new combined image. This paper provides an overview of different morphing techniques explaining how they work and discuss their features in some terms such as the morph visual quality, technical efficiency, and complexity, which can assist the researcher in the image morphing field to compare and identify morphing techniques that suit their working area. [ABSTRACT FROM AUTHOR]

This paper addresses the critical issue of fault detection and prediction in electric motor machinery, a prevalent challenge in industrial applications. Faults in these machines, stemming from mechanical or electrical issues, often lead to performance degradation or malfunctions, manifesting as abnormal signals in vibrations or currents. Our research focuses on enhancing the accuracy of fault classification in electric motor facilities, employing innovative image transformation methods—recurrence plots (RPs), the Gramian angular summation field (GASF), and the Gramian angular difference field (GADF)—in conjunction with a multi-input convolutional neural network (CNN) model. We conducted comprehensive experiments using datasets encompassing four types of machinery components: bearings, belts, shafts, and rotors. The results reveal that our multi-input CNN model exhibits exceptional performance in fault classification across all machinery types, significantly outperforming traditional single-input models. This study not only demonstrates the efficacy of advanced image transformation techniques in fault detection but also underscores the potential of multi-input CNN models in industrial fault diagnosis, paving the way for more reliable and efficient monitoring of electric motor machinery.

Building automation and the advancement of sustainability and safety in internal spaces benefit significantly from occupancy sensing. While particular traditional Machine Learning (ML) methods have succeeded at identifying occupancy patterns for specific datasets, achieving substantial performance in other datasets is still challenging. This paper proposes an occupancy detection method using non-intrusive ambient data and a Deep Learning (DL) model. An environmental sensing board was used to gather temperature, humidity, pressure, light level, motion, sound, and Carbon Dioxide (CO 2 ) data. The detection approach was deployed on an edge device to enable low-cost computing while increasing data security. The system was set up at a university office, which functioned as the primary case study testing location. We analyzed two Convolutional Neural Network (CNN) models to confirm the optimum alternative for edge deployment. A 2D-CNN technique was used for one day to identify occupancy in real-time. The model proved robust and reliable, with a 99.75% real-time prediction accuracy. [ABSTRACT FROM AUTHOR]

The scarcity of training annotation is one of the major challenges for the application of deep learning technology in medical image analysis. Recently, self‐supervised learning provides a powerful solution to alleviate this challenge by extracting useful features from a large number of unlabeled training data. In this article, we propose a simple and effective self‐supervised learning method for leukocyte classification by identifying the different transformations of leukocyte images, without requiring a large batch of negative sampling or specialized architectures. Specifically, a convolutional neural network backbone takes different transformations of leukocyte image as input for feature extraction. Then, a pretext task of self‐supervised transformation recognition on the extracted feature is conducted by a classifier, which helps the backbone learn useful representations that generalize well across different leukocyte types and datasets. In the experiment, we systematically study the effect of different transformation compositions on useful leukocyte feature extraction. Compared with five typical baselines of self‐supervised image classification, experimental results demonstrate that our method performs better in different evaluation protocols including linear evaluation, domain transfer, and finetuning, which proves the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Anomalies are a set of samples that do not follow the normal behavior of the majority of data. In an industrial dataset, anomalies appear in a very small number of samples. Currently, deep learning-based models have achieved important advances in image anomaly detection. However, with general models, real-world application data consisting of non-ideal images, also known as poison images, become a challenge. When the work environment is not conducive to consistently acquiring a good or ideal sample, an additional adaptive learning model is needed. In this work, we design a potential methodology to tackle poison or non-ideal images that commonly appear in industrial production lines by enhancing the existing training data. We propose Hierarchical Image Transformation and Multi-level Features (HIT-MiLF) modules for an anomaly detection network to adapt to perturbances from novelties in testing images. This approach provides a hierarchical process for image transformation during pre-processing and explores the most efficient layer of extracted features from a CNN backbone. The model generates new transformations of training samples that simulate the non-ideal condition and learn the normality in high-dimensional features before applying a Gaussian mixture model to detect the anomalies from new data that it has never seen before. Our experimental results show that hierarchical transformation and multi-level feature exploration improve the baseline performance on industrial metal datasets. [ABSTRACT FROM AUTHOR]

Omnidirectional optoelectronic systems (OOES) find applications in many areas where a wide viewing angle is crucial. The disadvantage of these systems is the large distortion of the images, which makes it difficult to make wide use of them. The purpose of this study is the development an algorithm for the precision calibration of an omnidirectional camera using a statistical approach. The calibration approach comprises three basic stages. The first stage is the formation of a cloud of points characterizing the view field of the virtual perspective camera. In the second stage, a calibration procedure that provides the projection function for the camera calibration is performed. The projection functions of traditional perspective lenses and omnidirectional wide-angle fisheye lenses with a viewing angle of no less than 180° are compared. The construction of the corrected image is performed in the third stage. The developed algorithm makes it possible to obtain an image for part of the field of view of an OOES by correcting the distortion from the original omnidirectional image.Using the developed algorithm, a non-mechanical pivoting camera based on an omnidirectional camera is implemented. The achieved mean squared error of the reproducing points from the original omnidirectional image onto the image with corrected distortion is less than the size of a very few pixels. [ABSTRACT FROM AUTHOR]

Geometric invariant feature representation plays an indispensable role in the field of image processing and computer vision. Recently, convolution neural networks (CNNs) have witnessed a great research progress, however CNNs do not excel at dealing with geometrically transformed images. Existing methods enhancing the ability of CNNs learning invariant feature representation rely partly on data augmentation or have a relatively weak generalization ability. This paper proposes orientation adaptive kernels (OA kernels) and orientation adaptive max pooling (OA max pooling) that comprise a new topological structure, orientation adaptive neural networks (OACNNs). OA kernels output the orientation feature maps which encode the orientation information of images. OA max pooling max-pools the orientation feature maps by automatically rotating the pooling windows according to their orientation. OA kernels and OA max pooling together allow for the eight orientation response of images to be computed, and then the max orientation response is obtained, which is proved to be a robust rotation invariant feature representation. OACNNs are compared with state-of-the-art methods and consistently outperform them in various experiments. OACNNs demonstrate a better generalization ability, yielding a test error rate 3.14 on the rotated images but only trained on "up-right" images, which outperforms all state-of-the-art methods by a large margin. [ABSTRACT FROM AUTHOR]

Visual properties that primarily attract bottom-up attention are collectively referred to as saliency. In this study, to understand the neural activity involved in top-down and bottom-up visual attention, we aim to prepare pairs of natural and unnatural images with common saliency. For this purpose, we propose an image transformation method based on deep neural networks that can generate new images while maintaining the consistent feature map, in particular the saliency map. This is an ill-posed problem because the transformation from an image to its corresponding feature map could be many-to-one, and in our particular case, the various images would share the same saliency map. Although stochastic image generation has the potential to solve such ill-posed problems, the most existing methods focus on adding diversity of the overall style/touch information while maintaining the naturalness of the generated images. To this end, we developed a new image transformation method that incorporates higher-dimensional latent variables so that the generated images appear unnatural with less context information but retain a high diversity of local image structures. Although such high-dimensional latent spaces are prone to collapse, we proposed a new regularization based on Kullback–Leibler divergence to avoid collapsing the latent distribution. We also conducted human experiments using our newly prepared natural and corresponding unnatural images to measure overt eye movements and functional magnetic resonance imaging, and found that those images induced distinctive neural activities related to top-down and bottom-up attentional processing. [ABSTRACT FROM AUTHOR]

It is time-consuming and expensive to take high-quality or high-resolution electron microscopy (EM) and fluorescence microscopy (FM) images. Taking these images could be even invasive to samples and may damage certain subtleties in the samples after long or intense exposures, often necessary for achieving high-quality or high-resolution in the first place. Advances in deep learning enable us to perform various types of microscopy image-to-image transformation tasks such as image denoising, super-resolution, and segmentation that computationally produce high-quality images from the physically acquired low-quality ones. When training image-to-image transformation models on pairs of experimentally acquired microscopy images, prior models suffer from performance loss due to their inability to capture inter-image dependencies and common features shared among images. Existing methods that take advantage of shared features in image classification tasks cannot be properly applied to image transformation tasks because they fail to preserve the equivariance property under spatial permutations, something essential in image-to-image transformation. To address these limitations, we propose the augmented equivariant attention networks (AEANets) with better capability to capture inter-image dependencies, while preserving the equivariance property. The proposed AEANets captures inter-image dependencies and shared features via two augmentations on the attention mechanism, which are the shared references and the batch-aware attention during training. We theoretically derive the equivariance property of the proposed augmented attention model and experimentally demonstrate its consistent superiority in both quantitative and visual results over the baseline methods. [ABSTRACT FROM AUTHOR]

Change detection (CD) with heterogeneous images is currently attracting extensive attention in remote sensing. In order to make heterogeneous images comparable, the image transformation methods transform one image into the domain of another image, which can simultaneously obtain a forward difference map (FDM) and backward difference map (BDM). However, previous methods only fuse the FDM and BDM in the post-processing stage, which cannot fundamentally improve the performance of CD. In this paper, a change alignment-based change detection (CACD) framework for unsupervised heterogeneous CD is proposed to deeply utilize the complementary information of the FDM and BDM in the image transformation process, which enhances the effect of domain transformation, thus improving CD performance. To reduce the dependence of the transformation network on labeled samples, we propose a graph structure-based strategy of generating prior masks to guide the network, which can reduce the influence of changing regions on the transformation network in an unsupervised way. More importantly, based on the fact that the FDM and BDM are representing the same change event, we perform change alignment during the image transformation, which can enhance the image transformation effect and enable FDM and BDM to effectively indicate the real change region. Comparative experiments are conducted with six state-of-the-art methods on five heterogeneous CD datasets, showing that the proposed CACD achieves the best performance with an average overall accuracy (OA) of 95.9 % on different datasets and at least 6.8 % improvement in the kappa coefficient. [ABSTRACT FROM AUTHOR]

The interest in coding was very high because it is widely relied on in the security of correspondence and in the security of information in addition to the need to rely on it in the storage of data because it leads to a pressure in the volume of information when storing it. In this research, image transformation was used to encode gray or color images by adopting parameters elected from contourlet transformations for image. The color images are acquired into the algorithm, to be converted into three slices (the main colors of the image), to be disassembled into their coefficients through contourlet transformations and then some high frequencies in addition to the low frequency are elected in order to reconstruct the image again. The election of low frequencies with a small portion of the high frequencies has led to bury some unnecessary information from the image components. The performance efficiency of the proposed method was measured by MSE and PSNR criteria to see the extent of the discrepancy between the original image and the recovered image when adopting different degrees of disassembly level, in addition, the extent to which the image type affects the performance efficiency of the approved method has been studied. When the practical application of the method show that the level of disassembly is directly proportional to the amount of the error square MSE and also has a great effect on the extent of correlation where the recovered image away from the original image in direct proportional with the increased degree of disassembly of the image. It also shows the extent to which it is affected by the image of different types and varieties, where was the highest value of the PSNR (58.0393) in the natural images and the less valuable in x-ray images (56.9295) as shown in table 4.

The synthesis between face sketches and face photos has important application values in law enforcement and digital entertainment. In cases of a lack of paired sketch-photo data, this paper proposes an unsupervised model to solve the problems of missing key facial details and a lack of realism in the synthesized images of existing methods. The model is built on the CycleGAN architecture. To retain more semantic information in the target domain, a multi-scale feature extraction module is inserted before the generator. In addition, the convolutional block attention module is introduced into the generator to enhance the ability of the model to extract important feature information. Via CBAM, the model improves the quality of the converted image and reduces the artifacts caused by image background interference. Next, in order to preserve more identity information in the generated photo, this paper constructs the multi-level cycle consistency loss function. Qualitative experiments on CUFS and CUFSF public datasets show that the facial details and edge structures synthesized by our model are clearer and more realistic. Meanwhile the performance indexes of structural similarity and peak signal-to-noise ratio in quantitative experiments are also significantly improved compared with other methods. [ABSTRACT FROM AUTHOR]

This study discriminates different lithological units of the Dokan Area, Kurdistan Region, NE-Iraq, using rapid-eye satellite data by image enhancement techniques, namely the false colour composite (FCC), optimum index factor (OIF), minimum noise fraction (MNF), principal component analysis (PCA) and band ratio (BR). Results of analyses show that the FCC (R: 5; G: 4: B: 1); MNF (R: 2, G: 3, B: 5); PCA (R: 5, G: 2, B: 1), and band ratio (R: 5/4, G: 2/1, B: 5/3) are the best to different geological formations. The results are confirmed in the field support with the geological maps available for the area. Geological formations appeared as a result of the collision process between the Arabian plate and the Iranian plate. In general, the study area is mountainous, which is usually represented by anticline folds with the main NW - SE trend in the study area, with very a rugged relief mainly due to the continuous collision between the Arabian plate and Iranian plate. The digital image processing of satellite data has demonstrated the sensor's capability and efficiency of the image processing methods in identifying and mapping geological units in the study area. [ABSTRACT FROM AUTHOR]

Introduction: being a structural and functional element of the state mechanism (a kind of “state within the state”), the prison system is transforming along with it. Accordingly, the image status of the prison itself and representatives of “prison authorities” and “prison population” is also changing. We bring to the fore the problem of understanding the term “system” in the context of the image status of the social system in general and the penal system in particular. We highlight the formation of semantic images and image statuses on the example of three social institutions (school, army, prison), which are similar in terms of parametric characteristics and functioning and qualitatively different in image status. The article comprehensively examines the bipolar image of the penal system: on the one hand, prison is inextricably linked with human misfortune, an evil that cannot be treated positively; on the other hand, as an instrument of state law enforcement policy, the prison guarantees the inevitability of punishment for a crime, ensuring the execution of punishment, protecting law-abiding citizens, which is a good thing for society and the state. Research materials and methods: the features of formation and functioning of the image status of the Russian penal (“prison”) system are considered in the context of the concept of cyclic political genesis. In accordance with this concept, in relation to the history of the unified Russian state, three cycles should be distinguished (imperial, Soviet, post-Soviet). Within the framework of each, Russia was represented by qualitatively different forms of state government, economic order, social structure, etc. At the same time, in such “different” Russian states, there were different models of prison systems, the formation and functioning of which, as well as the transformation of the image status, was carried out under the influence of state prison policy and under the influence of public consciousness (national mentality). Results: the current state of the Russian penal system can be described as transitional. Along with the legacy of the “Soviet past”, we observe serious changes proceeding from democratization and humanization of the political and legal system of the Russian Federation. Transformation of the image of the penal system is aimed at increasing the level of openness and forming a positive opinion about the functioning of the penitentiary system (the Concept for development until 2030). It is important that in the public consciousness the image of the penal system as a predominantly punitive prison system gradually be replaced by the idea of it as a penitentiary system, which is concerned primarily with “revival of the essence of humanity” in a person through awareness and repentance. As for the image status of employees of the penal system, the state can optimize it first of all by equalizing their official status with that of military personnel and special services employees, who, like representatives of the prison system, serve the Russian state, but are in a privileged position in relation to them. Increasing the prestige of the service in the penal system in the eyes of actual or potential employees implies the rejection of such differentiation.

Detecting hybrid tampering attacks in an image is extremely difficult; especially when copy-clone tampered segments exhibit identical illumination and contrast level about genuine objects. The existing method fails to detect tampering when the image undergoes hybrid transformation such as scaling, rotation, compression, and also fails to detect under smallsmooth tampering. The existing resampling feature extraction using the Deep learning techniques fails to obtain a good correlation among neighboring pixels in both horizontal and vertical directions. This work presents correlation aware convolution neural network (CA-CNN) for extracting resampling features for detecting hybrid tampering attacks. Here the image is resized for detecting tampering under a small-smooth region. The CA-CNN is composed of a three-layer horizontal, vertical, and correlated layer. The correlated layer is used for obtaining correlated resampling feature among horizontal sequence and vertical sequence. Then feature is aggregated and the descriptor is built. An experiment is conducted to evaluate the performance of the CA-CNN model over existing tampering detection methodologies considering the various datasets. From the result achieved it can be seen the CA-CNN is efficient considering various distortions and post-processing attacks such joint photographic expert group (JPEG) compression, and scaling. This model achieves much better accuracies, recall, precision, false positive rate (FPR), and F-measure compared existing methodologies. [ABSTRACT FROM AUTHOR]