Search

Traditional generative adversarial network models have made significant progress in generating high-quality images. However, there are still problems such as smooth edges of reconstructed images, distortion of details, and color shifts in generated images. In this regard, this paper proposes a new improved generative adversarial network image super-resolution reconstruction RSC-WSRGAN model. This model redesigns the residual block in the super-resolution using a generative adversarial network generator network and removes the batch normalization (BN) layer in the residual block, introduce RFAConv, replace the original rectified linear unit activation function with the smooth maximum unit activation function, and add the convolution attention module CBAM to build the RSC module. The model's focus on features is enhanced, improving the detail and clarity of the reconstructed image. In addition, Wasserstein distance is used to replace the JS divergence that measures the data distribution in the generative adversarial network to optimize the network training process. It also solves the problem of gradient disappearance due to the removal of the BN layer, making the network training process more stable. At the same time, the loss function is improved to better quantify the error between the reconstructed image and the real image, the network model is optimized, and the quality of the generated image is improved. Finally, the improved RSC-WSRGAN image super-resolution reconstruction model was used to conduct reconstruction experiments on the Div2k data set. The results showed that compared with the original model value, the PSNR was improved by 0.534 dB, the SSIM value was improved by 0.038, and the LPIPS value was optimized by 0.018. Image reconstruction experiments were conducted with other mainstream models on public general data sets such as Set5, Set14, and BSD100. The results show that the model proposed in this article further strengthens the edge contour of the reconstructed image, and the color does not suffer from distortion or offset. The overall visual quality is better, the look and feel has been significantly improved, and the realism of the reconstructed image has been improved. [ABSTRACT FROM AUTHOR]

Star anise, a widely popular spice, benefits from classification that enhances its economic value. In response to the low identification efficiency and accuracy of star anise varieties in the market, as well as the scarcity of related research, this study proposes an efficient identification method based on non-similarity augmentation and a lightweight cascaded neural network. Specifically, this approach utilizes a Siamese enhanced data network and a front-end SRGAN network to address sample imbalance and the challenge of identifying blurred images. The YOLOv8 model is further lightweight to reduce memory usage and increase detection speed, followed by optimization of the weight parameters through an extended training strategy. Additionally, a diversified fusion dataset of star anise, incorporating open data, was constructed to further validate the feasibility and effectiveness of this method. Testing showed that the SA-SRYOLOv8 detection model achieved an average detection precision (mAP) of 96.37%, with a detection speed of 146 FPS. Ablation experiment results showed that compared to the original YOLOv8 and the improved YOLOv8, the cascade model's mAP increased by 0.09 to 0.81 percentage points. Additionally, when compared to mainstream detection models such as SSD, Fast R-CNN, YOLOv3, YOLOv5, YOLOX, and YOLOv7, the cascade model's mAP increased by 1.81 to 19.7 percentage points. Furthermore, the model was significantly lighter, at only about 7.4% of the weight of YOLOv3, and operated at twice the speed of YOLOv7. Visualization results demonstrated that the cascade model accurately detected multiple star anise varieties across different scenarios, achieving high-precision detection targets. The model proposed in this study can provide new theoretical frameworks and ideas for constructing real-time star anise detection systems, offering new technological applications for smart agriculture. [ABSTRACT FROM AUTHOR]

Defects in additive manufacturing processes are closely related to the mechanical and physical properties of the components. However, the extreme conditions of high temperatures, intense light, and powder during the manufacturing process present significant challenges for defect detection. Additionally, the high reflectivity of metallic components can cause pixels in image sensors to become overexposed, resulting in the loss of many defect signals. Thus, this paper mainly focuses on proposing an accurate inspection and super-resolution reconstruction method for additive manufactured defects based on Stokes vector and deep learning, where the Stokes vectors, polarization degree, and polarization angles of the inspected defects are effectively utilized to suppress the high reflectivity of metallic surfaces, enhance the contrast of defect regions, and highlight the boundaries of defects. Furthermore, a modified SRGAN model designated SRGAN-H is presented by employing an additional convolutional layer and activation functions, including Harswish and Tanh, to accelerate the convergence of the SRGAN-H network and improve the reconstruction of the additive manufactured defect region. The experiment results demonstrated that the SRGAN-H model outperformed SRGAN and traditional SR reconstruction algorithms in terms of the images of Stokes vectors, polarization degree, and polarization angles. For the scratch and hole test sets, the PSNR values were 33.405 and 31.159, respectively, and the SSIM values were 0.890 and 0.896, respectively. These results reflect the effectiveness of the SRGAN-H model in super-resolution reconstruction of scratch and hole images. For the scratch and hole images chosen in this study, the PSNR values of SRGAN-H for single image super-resolution reconstruction ranged from 31.86786 to 43.82374, higher than the results obtained by the pre-improvement SRGAN algorithm. [ABSTRACT FROM AUTHOR]

Object detection in high resolution enables the identification and localization of objects for monitoring critical areas with precision. Although there have been improvements in object detection at high resolution, the variety of object scales, as well as the diversity of backgrounds and textures in high-resolution images, make it challenging for detectors to generalize successfully. This study introduces a new method for object detection in high-resolution images. The pre-processing stage of the method includes ISA and SAM to slice the input image and segment the objects in bounding boxes, respectively. In order to improve the resolution in the slices, the first layer of YOLO is designed as SRGAN. Thus, before applying YOLO detection, the resolution of the sliced images is increased to improve features. The proposed system is evaluated on xView and VisDrone datasets for object detection algorithms in satellite and aerial imagery contexts. The success of the algorithm is presented in four different YOLO architectures integrated with SRGAN. According to comparative evaluations, the proposed system with Yolov5 and Yolov8 produces the best results on xView and VisDrone datasets, respectively. Based on the comparisons with the literature, our proposed system produces better results. [ABSTRACT FROM AUTHOR]

Wavefront Coding (WFC) is an innovative technique aimed at extending the depth of focus (DOF) of optics imaging systems. In digital imaging systems, super-resolution digital reconstruction close to the diffraction limit of optical systems has always been a hot research topic. With the design of a point spread function (PSF) generated by a suitably phase mask, WFC could also be used in super-resolution image reconstruction. In this paper, we use a deep learning network combined with WFC as a general framework for images reconstruction, and verify its possibility and effectiveness. Considering the blur and additive noise simultaneously, we proposed three super-resolution image reconstruction procedures utilizing convolutional neural networks (CNN) based on mean square error (MSE) loss, conditional Generative Adversarial Networks (CGAN), and Swin Transformer Networks (SwinIR) based on mean absolute error (MAE) loss. We verified their effectiveness by simulation experiments. A comparison of experimental results shows that the SwinIR deep residual network structure based on MAE loss optimization criteria can generate more realistic super-resolution images with more details. In addition, we used a WFC camera to obtain a resolution test target and real scene images for experiments. Using the resolution test target, we demonstrated that the spatial resolution could be improved from 55.6 lp/mm to 124 lp/mm by the proposed super-resolution reconstruction procedure. The reconstruction results show that the proposed deep learning network model is superior to the traditional method in reconstructing high-frequency details and effectively suppressing noise, with the resolution approaching the diffraction limit. [ABSTRACT FROM AUTHOR]

Colorectal cancer (CRC) is the second leading cause of cancer-related deaths worldwide. Colonoscopy is the primary method to prevent CRC. However, traditional polyp detection methods face problems such as low image resolution and the possibility of missing polyps. In recent years, deep learning techniques have been extensively employed in the detection of colorectal polyps. However, these algorithms have not yet addressed the issue of detection in low-resolution images. In this study, we propose a novel YOLO-SRPD model by integrating SRGAN and YOLO to address the issue of low-resolution colonoscopy images. Firstly, the SRGAN with integrated ACmix is used to convert low-resolution images to high-resolution images. The generated high-resolution images are then used as the training set for polyp detection. Then, the C3_Res2Net is integrated into the YOLOv5 backbone to enhance multiscale feature extraction. Finally, CBAM modules are added before the prediction head to enhance attention to polyp information. The experimental results indicate that YOLO-SRPD achieves a mean average precision (mAP) of 94.2% and a precision of 95.2%. Compared to the original model (YOLOv5), the average accuracy increased by 1.8% and the recall rate increased by 5.6%. These experimental results confirm that YOLO-SRPD can address the low-resolution problem during colorectal polyp detection and exhibit exceptional robustness. [ABSTRACT FROM AUTHOR]

The classification of White Blood Cells (WBCs) is crucial for diagnosing diseases, monitoring treatment effectiveness, and understanding how the immune system functions. In this paper, we propose a deep learning approach to classify WBCs using Super Resolution Generative Adversarial Network (SRGAN) and Visual Geometry Group 19 (VGG19). Firstly, microscopic images of WBCs are generated using the SRGAN to obtain more precise and high-resolution images, which are then classified with a pretrained VGG19 classifier. Low-resolution (LR) images are inputted into the generator of SRGAN, and its discriminator compares the High-resolution (HR) image with LR, generating super-resolution images to minimize misclassification risks. A large dataset of 12,447 images containing four classes of WBCs (Eosinophil, Lymphocyte, Monocyte, and Neutrophil) is utilized to train and validate our proposed model. Following extensive experimental analysis, our proposed model achieves a test accuracy of 94.87 %, surpassing traditional Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Hybrid CNN-RNN models, and other conventional approaches. The generated images of SRGAN overcome challenges associated with misclassification due to the poor resolution of microscopic images, while the use of a pretrained model as a classifier reduces classification complexity. The source code of the entire work is available at https://github.com/Jannatul-Ferdousi/SRGAN_VGG19_WBC.git.

Copyright of Journal of Henan Agricultural Sciences is the property of Editorial Board of Journal of Henan Agricultural Sciences and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Periodontal disease is a widespread global health concern that necessitates an accurate diagnosis for effective treatment. Traditional diagnostic methods based on panoramic radiographs are often limited by subjective evaluation and low-resolution imaging, leading to suboptimal precision. This study presents an approach that integrates Super-Resolution Generative Adversarial Networks (SRGANs) with deep learning-based segmentation models to enhance the segmentation of periodontal bone loss (PBL) areas on panoramic radiographs. By transforming low-resolution images into high-resolution versions, the proposed method reveals critical anatomical details that are essential for precise diagnostics. The effectiveness of this approach was validated using datasets from the Chungbuk National University Hospital and the Kaggle data portal, demonstrating significant improvements in both image resolution and segmentation accuracy. The SRGAN model, evaluated using the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) metrics, achieved a PSNR of 30.10 dB and an SSIM of 0.878, indicating high fidelity in image reconstruction. When applied to semantic segmentation using a U-Net architecture, the enhanced images resulted in a dice similarity coefficient (DSC) of 0.91 and an intersection over union (IoU) of 84.9%, compared with 0.72 DSC and 65.4% IoU for native low-resolution images. These results underscore the potential of SRGAN-enhanced imaging to improve PBL area segmentation and suggest broader applications in medical imaging, where enhanced image clarity is crucial for diagnostic accuracy. This study also highlights the importance of further research to expand the dataset diversity and incorporate clinical validation to fully realize the benefits of super-resolution techniques in medical diagnostics.

Star anise, a widely popular spice, benefits from classification that enhances its economic value. In response to the low identification efficiency and accuracy of star anise varieties in the market, as well as the scarcity of related research, this study proposes an efficient identification method based on non-similarity augmentation and a lightweight cascaded neural network. Specifically, this approach utilizes a Siamese enhanced data network and a front-end SRGAN network to address sample imbalance and the challenge of identifying blurred images. The YOLOv8 model is further lightweight to reduce memory usage and increase detection speed, followed by optimization of the weight parameters through an extended training strategy. Additionally, a diversified fusion dataset of star anise, incorporating open data, was constructed to further validate the feasibility and effectiveness of this method. Testing showed that the SA-SRYOLOv8 detection model achieved an average detection precision (mAP) of 96.37%, with a detection speed of 146 FPS. Ablation experiment results showed that compared to the original YOLOv8 and the improved YOLOv8, the cascade model’s mAP increased by 0.09 to 0.81 percentage points. Additionally, when compared to mainstream detection models such as SSD, Fast R-CNN, YOLOv3, YOLOv5, YOLOX, and YOLOv7, the cascade model’s mAP increased by 1.81 to 19.7 percentage points. Furthermore, the model was significantly lighter, at only about 7.4% of the weight of YOLOv3, and operated at twice the speed of YOLOv7. Visualization results demonstrated that the cascade model accurately detected multiple star anise varieties across different scenarios, achieving high-precision detection targets. The model proposed in this study can provide new theoretical frameworks and ideas for constructing real-time star anise detection systems, offering new technological applications for smart agriculture.

Defects in additive manufacturing processes are closely related to the mechanical and physical properties of the components. However, the extreme conditions of high temperatures, intense light, and powder during the manufacturing process present significant challenges for defect detection. Additionally, the high reflectivity of metallic components can cause pixels in image sensors to become overexposed, resulting in the loss of many defect signals. Thus, this paper mainly focuses on proposing an accurate inspection and super-resolution reconstruction method for additive manufactured defects based on Stokes vector and deep learning, where the Stokes vectors, polarization degree, and polarization angles of the inspected defects are effectively utilized to suppress the high reflectivity of metallic surfaces, enhance the contrast of defect regions, and highlight the boundaries of defects. Furthermore, a modified SRGAN model designated SRGAN-H is presented by employing an additional convolutional layer and activation functions, including Harswish and Tanh, to accelerate the convergence of the SRGAN-H network and improve the reconstruction of the additive manufactured defect region. The experiment results demonstrated that the SRGAN-H model outperformed SRGAN and traditional SR reconstruction algorithms in terms of the images of Stokes vectors, polarization degree, and polarization angles. For the scratch and hole test sets, the PSNR values were 33.405 and 31.159, respectively, and the SSIM values were 0.890 and 0.896, respectively. These results reflect the effectiveness of the SRGAN-H model in super-resolution reconstruction of scratch and hole images. For the scratch and hole images chosen in this study, the PSNR values of SRGAN-H for single image super-resolution reconstruction ranged from 31.86786 to 43.82374, higher than the results obtained by the pre-improvement SRGAN algorithm.

Monitoring medical therapy remains a challenging task across all non‐surgical skin cancer treatment modalities. In addition, confirmation of residual tumours after treatment is essential for the early detection of potential relapses. Optical coherence tomography (OCT), a non‐invasive method for real‐time cross‐sectional imaging of living tissue, is a promising imaging approach for assessing relatively flat, near‐surface skin lesions, such as those that occur in most basal cell carcinomas (BCCs), at the time of diagnosis. However, the skin's inherent property of strong light scattering impedes the implementation of OCT in these cases due to the poor image quality. Furthermore, translating OCT's optical parameters into practical use in routine clinical settings is complicated due to substantial observer subjectivity. In this retrospective pilot study, we developed a workflow based on the upscale of the OCT images resolution using a deep generative adversarial network and the estimation of the skin optical attenuation coefficient. At the site of immunocryosurgery‐treated BCC, the proposed methodology can extract optical parameters and discriminate objectively between tumour foci and scar tissue. [ABSTRACT FROM AUTHOR]

Aiming to quickly and accurately detect abnormal behaviors of workers in central control rooms, such as playing mobile phone and sleeping, an abnormal behavior detection algorithm based on improved YOLOv5 is proposed. The technique uses SRGAN to reconstruct the input image to improve the resolution and enhance the detailed information. Then, the MnasNet is introduced to replace the backbone feature extraction network of the original YOLOv5, which could achieve the lightweight of the model. Moreover, the detection accuracy of the whole network is enhanced by adding the ECA-Net attention mechanism into the feature fusion network structure of YOLOv5 and modifying the loss function as EIOU. The experimental results in the custom dataset show that compared with the original YOLOv5 algorithm, the algorithm proposed in this paper improves the detection speed to 75.50 frames/s under the condition of high detection accuracy, which meets the requirements of real-time detection. Meanwhile, compared with other mainstream behavior detection algorithms, this algorithm also shows better detection performance. [ABSTRACT FROM AUTHOR]

Object detection in high resolution enables the identification and localization of objects for monitoring critical areas with precision. Although there have been improvements in object detection at high resolution, the variety of object scales, as well as the diversity of backgrounds and textures in high-resolution images, make it challenging for detectors to generalize successfully. This study introduces a new method for object detection in high-resolution images. The pre-processing stage of the method includes ISA and SAM to slice the input image and segment the objects in bounding boxes, respectively. In order to improve the resolution in the slices, the first layer of YOLO is designed as SRGAN. Thus, before applying YOLO detection, the resolution of the sliced images is increased to improve features. The proposed system is evaluated on xView and VisDrone datasets for object detection algorithms in satellite and aerial imagery contexts. The success of the algorithm is presented in four different YOLO architectures integrated with SRGAN. According to comparative evaluations, the proposed system with Yolov5 and Yolov8 produces the best results on xView and VisDrone datasets, respectively. Based on the comparisons with the literature, our proposed system produces better results.

An emergency risk assessment by collecting disaster-affected images via unmanned aerial vehicles is the current norm. Reasonable rescue planning and resource allocation depend on a quick and precise semantic interpretation of natural disaster images. However, the poor image quality produced by various technological and environmental factors and complex scenarios associated with disaster-affected regions makes the classification operation challenging. In order to get in-depth spatial features for decoding the intricate textures associated with catastrophe images, this study proposes an implementation of the CNN-based multibranch feature extraction technique. An advanced mixed-attention mechanism is exploited to extract the highly essential features. This mixed-attention mechanism effectively overcomes the flaws generated by traditional convolution by neglecting the global information and focusing on local key features. An SRGAN-based super-resolution method is utilized to acquire high-resolution images with rich spatial details to enhance the quality of aerial images. Besides, we experiment with several existing image classification algorithms, such as the ensemble model of pre-trained networks, the capsule network model, and the stacked autoencoder. Finally, we perform a comparative analysis between all the deployed models to obtain the best-performing classifier. Our proposed multibranch feature extraction with mixed-attention mechanism-based network performs more superiorly among the four models due to its ability to extract highly relevant features from disaster images. Generated super-resolution images effectively increase the classification performance. Our research findings and approaches accommodate quality resources for disaster image quality enhancement and classification activities. [ABSTRACT FROM AUTHOR]

As a classic visual task, super-resolution has a wide range of applications in many fields. With the development of unsupervised learning in deep learning and the proposal of GANs in generative adversarial networks, super-resolution technology has been further improved, but related networks still have many problems such as overfitting and weak generalization. Based on SRGAN, inspired by the relevant papers studying the influence of Dropout in classical super-resolution networks, layer was added to SRGAN and its influence on the quality of the generated image was studied. The image quality was evaluated with the peak signal-to-noise ratio PSNR (peak signal to noise ratio) and structural similarity SSIM( structural similarity). And the experimental results show that the network reconstructed image has better visual effects under suitable dropout parameters. The PSNR value can reach an increase of about 0. 4, and SSIM is also improved, and from the comparison of images generated by different iterations in the training process, it is found that the improved network alleviates the problem of training instability. Adding the layer to a super-resolution network is different from previous methods and provides a new way to improve such networks. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel approach to address the challenges of Super-Resolution Generative Adversarial Network (SRGAN) in face image super-resolution reconstruction. We introduce a new improved SRGAN algorithm, named Wasserstein SRGAN (W-SRGAN), which addresses the limitations of the original model by enhancing the loss function, generator, and discriminator. Our approach utilizes the embedded residual structure combined with feature fusion as the new generator, while removing the Sigmoid of the last layer of the discriminator of SRGAN by borrowing the idea of Wasserstein GAN (W-GAN). Additionally, we replace the Kullback–Leibler (KL) divergence of SRGAN with Wasserstein distance. The contributions of our research are twofold. Firstly, we propose a new face super-resolution reconstruction algorithm that outperforms existing methods in terms of visual quality. Secondly, we introduce a new loss function and generator–discriminator architecture that can be applied to other image super-resolution tasks, extending the applicability of GANs in this domain. Experimental results demonstrate that our proposed W-SRGAN outperforms Bicubic, Super-Resolution Convolutional Neural Network (SRCNN), and SRGAN in terms of visual quality on all Celeb A datasets. These results confirm the effectiveness of our proposed algorithm and provide a new solution for face super-resolution reconstruction. [ABSTRACT FROM AUTHOR]

Image super-resolution reconstruction technology can boost image resolution and aid in the discovery of PCB flaws. The traditional SRGAN algorithm produces reconstructed images with great realism, but it also has the disadvantages of insufficient feature information extraction ability, a large number of model parameters, as well as a lack of fine-grained image reconstruction impact. To that end, this paper proposes an SRGAN-based super-resolution reconstruction algorithm for PCB defect images that is the first to add a VIT network to the generation network to extend the perceptual field and improve the model's ability to extract high-frequency information. The high-frequency feature extraction module is then used to enhance the generator's extraction of high-frequency information from the feature map while reducing the complexity of the model network. Finally, the inverted residual module and VIT network are combined to form the discriminator's backbone network, which extracts and summarizes shallow features while synthesizing global features for higher-level features, allowing the discriminator effect to be achieved with less spatial complexity. On the test set, the improved algorithm increases the PSNR by 0.82 and the SSIM by 0.03, and the SRVIT algorithm's number of discriminator model parameters and model space size are decreased by 2.01 M and 7.5 MB, respectively, when compared to the SRGAN algorithm. Moreover, the improved PCB defect image super-resolution reconstruction algorithm not only enhances the image reconstruction effect but also lowers model space complexity. [ABSTRACT FROM AUTHOR]

It is difficult for laser scanning confocal microscopy to obtain high- or ultra-highresolution laser confocal images directly, which affects the deep mining and use of the embedded information in laser confocal images and forms a technical bottleneck in the in-depth exploration of the microscopic physiological and biochemical processes of plants. The super-resolution reconstruction model (SRGAN), which is based on a generative adversarial network and superresolution reconstruction model (SRResNet), which is based on a residual network, was used to obtain single and secondary super-resolution reconstruction images of laser confocal images of the root cells of the hyperaccumulator Solanum nigrum. Using the peak signal-to-noise ratio (PSNR), structural similarity (SSIM) and mean opinion score (MOS), the models were evaluated by the image effects after reconstruction and were applied to the recognition of endocytic vesicles in Solanum nigrum root cells. The results showed that the single reconstruction and the secondary reconstruction of SRGAN and SRResNet improved the resolution of laser confocal images. PSNR, SSIM, and MOS were clearly improved, with a maximum PSNR of 47.690. The maximum increment of PSNR and SSIM of the secondary reconstruction images reached 21.7% and 2.8%, respectively, and the objective evaluation of the image quality was good. However, overall MOS was less than that of the single reconstruction, the perceptual quality was weakened, and the time cost was more than 130 times greater. The reconstruction effect of SRResNet was better than that of SRGAN. When SRGAN and SRResNet were used for the recognition of endocytic vesicles in Solanum nigrum root cells, the clarity of the reconstructed images was obviously improved, the boundary of the endocytic vesicles was clearer, and the number of identified endocytic vesicles increased from 6 to 9 and 10, respectively, and the mean fluorescence intensity was enhanced by 14.4% and 7.8%, respectively. Relevant research and achievements are of great significance for promoting the application of deep learning methods and image super-resolution reconstruction technology in laser confocal image studies. [ABSTRACT FROM AUTHOR]

Copyright of Eastern-European Journal of Enterprise Technologies is the property of PC TECHNOLOGY CENTER and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Vehicle license plate images are often low resolution and blurry because of the large distance and relative motion between the vision sensor and vehicle, making license plate identification arduous. The extensive use of expensive, high-quality vision sensors is uneconomical in most cases; thus, images are initially captured and then translated from low resolution to high resolution. For this purpose, several traditional techniques such as bilinear, bicubic, super-resolution convolutional neural network, and super-resolution generative adversarial network (SRGAN) have been developed over time to upgrade low-quality images. However, most studies in this area pertain to the conversion of low-resolution images to super-resolution images, and little attention has been paid to motion de-blurring. This work extends SRGAN by adding an intelligent motion-deblurring method (termed SRGAN-LP), which helps to enhance the image resolution and remove motion blur from the given images. A comprehensive and new domain-specific dataset was developed to achieve improved results. Moreover, maintaining higher quantitative and qualitative results in comparison to the ground truth images, this study upscales the provided low-resolution image four times and removes the motion blur to a reasonable extent, making it suitable for surveillance applications. [ABSTRACT FROM AUTHOR]

Image super-resolution reconstruction technology can boost image resolution and aid in the discovery of PCB flaws. The traditional SRGAN algorithm produces reconstructed images with great realism, but it also has the disadvantages of insufficient feature information extraction ability, a large number of model parameters, as well as a lack of fine-grained image reconstruction impact. To that end, this paper proposes an SRGAN-based super-resolution reconstruction algorithm for PCB defect images that is the first to add a VIT network to the generation network to extend the perceptual field and improve the model’s ability to extract high-frequency information. The high-frequency feature extraction module is then used to enhance the generator’s extraction of high-frequency information from the feature map while reducing the complexity of the model network. Finally, the inverted residual module and VIT network are combined to form the discriminator’s backbone network, which extracts and summarizes shallow features while synthesizing global features for higher-level features, allowing the discriminator effect to be achieved with less spatial complexity. On the test set, the improved algorithm increases the PSNR by 0.82 and the SSIM by 0.03, and the SRVIT algorithm’s number of discriminator model parameters and model space size are decreased by 2.01 M and 7.5 MB, respectively, when compared to the SRGAN algorithm. Moreover, the improved PCB defect image super-resolution reconstruction algorithm not only enhances the image reconstruction effect but also lowers model space complexity.

Insulators are important safety devices on high-voltage transmission lines. An insulator inspection system based on UAVs is widely used. Insulator defect detection is performed against two main engineering problems: 1. The scarcity of defect images, which leads to a network overfitting problem. 2. The small object detection, which is caused by the long aerial photography distance, and the low resolution of the insulator defect area pictures. In this study, firstly, the super-resolution reconstruction method is used to augment the dataset, which can not only solve the overfitting problem but also enrich the image texture features and pixel values of defect areas. Secondly, in the process of insulator defect detection, a two-stage cascading method is used. In the first stage, the rotated object detection algorithm is used to realize the object location of insulator strings, and then images of the identified insulators are cropped to reduce the proportion of the background area in defect images. In the second stage, YOLO v5 is used for the detection of insulator caps that are missing defects. The method proposed shows good detection effect on the self-built training set which contains only 85 images captured from real inspection environments. The method has practical industrial application value. [ABSTRACT FROM AUTHOR]

The difficulty of defining the depth of near-shore seas (bathymetry) arises from the limits imposed by traditional ship-based approaches during data collection. Although LiDAR sensors with green lasers have been used to solve some of these problems, they come at a high cost in terms of their footprint and are prone to inaccuracies in turbid water. As shorelines undergo changes due to erosion, wetland loss, hurricane effects, sea-level rise, urban development, and population growth, consistent and accurate bathymetric data become crucial. These data play a significant role in comprehending and managing sensitive interfaces between land and water. Satellite-derived Bathymetry (SDB), which has been described by maritime and remote sensing researchers for over 50 years, emerges as a gap-filler, encompassing bathymetry extraction approaches using active (altimetry) and passive (optics) satellite sensors. In the past decade, advancements in sensor capabilities, computational power, and recognition by the International Hydrographic Organization (IHO) have propelled SDB to unprecedented popularity. This study explores the contribution of super-resolution in SDB for the first time in the shallow water zone of Horseshoe Island, Antarctica. Random forest and extreme gradient boosting machine learning-based regressors were used on Landsat-8 OLI images, which were atmospherically corrected by the ACOLITE algorithm and spatially enhanced twofold via the generative adversarial network for single image super-resolution (SRGAN). The bathymetry predictions with these two machine learning algorithms on SR images were benchmarked against previous studies in the same region and showed admissible results concerning the IHO standards. Furthermore, the results indicate that the bathymetric inversion performance of the spatially enhanced image via SRGAN is superior to the original multispectral image and pan-sharpened image in terms of the metrics observed, namely, root mean square error (RMSE), mean average error (MAE), and coefficient of determination (R2). Comparison between the original and SR image bathymetry inversion for the 0–15 m depth range indicate improvements of up to 0.13 m for RMSE, up to 0.30 m for MAE, and up to 11% for R2. These results promise possible effective usage of super-resolution in SDB with satellite images such as Sentinel −2, which do not include a panchromatic band. • Study conducts a unique satellite bathymetry approach with use of super-resolution. • Super-resolved Landsat 8 image provided higher bathymetric inversion accuracy. • The Random Forest and XgBoost algorithms provided acceptable bathymetric inversions. [ABSTRACT FROM AUTHOR]

In the realm of image processing, enhancing the quality of the images is known as a superresolution problem (SR). Among SR methods, a super-resolution generative adversarial network, or SRGAN, has been introduced to generate SR images from low-resolution images. As it is of the utmost importance to keep the size and the shape of the images, while enlarging the medical images, we propose a novel super-resolution model with a generative adversarial network to generate SR images with finer details and higher quality to encourage less blurring. By widening residual blocks and using a self-attention layer, our model becomes robust and generalizable as it is able to extract the most important part of the images before up-sampling. We named our proposed model as wide-attention SRGAN (WA-SRGAN). Moreover, we have applied improved Wasserstein with a Gradient penalty to stabilize the model while training. To train our model, we have applied images from Camylon 16 database and enlarged them by 2×, 4×, 8×, and 16× upscale factors with the ground truth of the size of 256 × 256 × 3. Furthermore, two normalization methods, including batch normalization, and weight normalization have been applied and we observed that weight normalization is an enabling factor to improve metric performance in terms of SSIM. Moreover, several evaluation metrics, such as PSNR, MSE, SSIM, MS-SSIM, and QILV have been applied for having a comprehensive objective comparison with other methods, including SRGAN, A-SRGAN, and bicubial. Also, we performed the job of classification by using a deep learning model called ResNeXt-101 (32 × 8d) for super-resolution, high-resolution, and low-resolution images and compared the outcomes in terms of accuracy score. Finally, the results on breast cancer histopathology images show the superiority of our model by using weight normalization and a batch size of one in terms of restoration of the color and the texture details.

Vehicle license plate images are often low resolution and blurry because of the large distance and relative motion between the vision sensor and vehicle, making license plate identification arduous. The extensive use of expensive, high-quality vision sensors is uneconomical in most cases; thus, images are initially captured and then translated from low resolution to high resolution. For this purpose, several traditional techniques such as bilinear, bicubic, super-resolution convolutional neural network, and super-resolution generative adversarial network (SRGAN) have been developed over time to upgrade low-quality images. However, most studies in this area pertain to the conversion of low-resolution images to super-resolution images, and little attention has been paid to motion de-blurring. This work extends SRGAN by adding an intelligent motion-deblurring method (termed SRGAN-LP), which helps to enhance the image resolution and remove motion blur from the given images. A comprehensive and new domain-specific dataset was developed to achieve improved results. Moreover, maintaining higher quantitative and qualitative results in comparison to the ground truth images, this study upscales the provided low-resolution image four times and removes the motion blur to a reasonable extent, making it suitable for surveillance applications.

Colon cancer is thought about as the third most regularly identified cancer after Brest and lung cancer. Most colon cancers are adenocarcinomas developing from adenomatous polyps, grow on the intima of the colon. The standard procedure for polyp detection is colonoscopy, where the success of the standard colonoscopy depends on the colonoscopist experience and other environmental factors. Nonetheless, throughout colonoscopy procedures, a considerable number (8-37%) of polyps are missed due to human mistakes, and these missed polyps are the prospective reason for colorectal cancer cells. In the last few years, many research groups developed deep learning-based computer-aided (CAD) systems that recommended many techniques for automated polyp detection, localization, and segmentation. Still, accurate polyp detection, segmentation is required to minimize polyp miss out rates. This paper suggested a Super-Resolution Generative Adversarial Network (SRGAN) assisted Encoder-Decoder network for fully automated colon polyp segmentation from colonoscopic images. The proposed deep learning model incorporates the SRGAN in the up-sampling process to achieve more accurate polyp segmentation. We examined our model on the publicly available benchmark datasets CVC-ColonDB and Warwick-QU. The model accomplished a dice score of 0.948 on the CVC-ColonDB dataset, surpassed the recently advanced state-of-the-art (SOTA) techniques. When it is evaluated on the Warwick-QU dataset, it attains a Dice Score of 0.936 on part A and 0.895 on Part B. Our model showed more accurate results for sessile and smaller-sized polyps. [ABSTRACT FROM AUTHOR]

In this study, we have proposed an algorithm that solves the problems which occur during the recognition of a vehicle license plate through closed-circuit television (CCTV) by using a deep learning model trained with a general database. The deep learning model which is commonly used suffers with a disadvantage of low recognition rate in the tilted and low-resolution images, as it is trained with images acquired from the front of the license plate. Furthermore, the vehicle images acquired by using CCTV have issues such as limitation of resolution and perspective distortion. Such factors make it difficult to apply the commonly used deep learning model. To improve the recognition rate, an algorithm which is a combination of the super-resolution generative adversarial network (SRGAN) model, and the perspective distortion correction algorithm is proposed in this paper. The accuracy of the proposed algorithm was verified with a character recognition algorithm YOLO v2, and the recognition rate of the vehicle license plate image was improved 8.8% from the original images. [ABSTRACT FROM AUTHOR]

Insulators are important safety devices on high-voltage transmission lines. An insulator inspection system based on UAVs is widely used. Insulator defect detection is performed against two main engineering problems: 1. The scarcity of defect images, which leads to a network overfitting problem. 2. The small object detection, which is caused by the long aerial photography distance, and the low resolution of the insulator defect area pictures. In this study, firstly, the super-resolution reconstruction method is used to augment the dataset, which can not only solve the overfitting problem but also enrich the image texture features and pixel values of defect areas. Secondly, in the process of insulator defect detection, a two-stage cascading method is used. In the first stage, the rotated object detection algorithm is used to realize the object location of insulator strings, and then images of the identified insulators are cropped to reduce the proportion of the background area in defect images. In the second stage, YOLO v5 is used for the detection of insulator caps that are missing defects. The method proposed shows good detection effect on the self-built training set which contains only 85 images captured from real inspection environments. The method has practical industrial application value.

In this study, we have proposed an algorithm that solves the problems which occur during the recognition of a vehicle license plate through closed-circuit television (CCTV) by using a deep learning model trained with a general database. The deep learning model which is commonly used suffers with a disadvantage of low recognition rate in the tilted and low-resolution images, as it is trained with images acquired from the front of the license plate. Furthermore, the vehicle images acquired by using CCTV have issues such as limitation of resolution and perspective distortion. Such factors make it difficult to apply the commonly used deep learning model. To improve the recognition rate, an algorithm which is a combination of the super-resolution generative adversarial network (SRGAN) model, and the perspective distortion correction algorithm is proposed in this paper. The accuracy of the proposed algorithm was verified with a character recognition algorithm YOLO v2, and the recognition rate of the vehicle license plate image was improved 8.8% from the original images.

Copyright of Journal of Image & Graphics is the property of Editorial Office of Journal of Image & Graphics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Detailed and accurate information on the spatial variation of land cover and land use is a critical component of local ecology and environmental research. For these tasks, high spatial resolution images are required. Considering the trade-off between high spatial and high temporal resolution in remote sensing images, many learning-based models (e.g., Convolutional neural network, sparse coding, Bayesian network) have been established to improve the spatial resolution of coarse images in both the computer vision and remote sensing fields. However, data for training and testing in these learning-based methods are usually limited to a certain location and specific sensor, resulting in the limited ability to generalize the model across locations and sensors. Recently, generative adversarial nets (GANs), a new learning model from the deep learning field, show many advantages for capturing high-dimensional nonlinear features over large samples. In this study, we test whether the GAN method can improve the generalization ability across locations and sensors with some modification to accomplish the idea “training once, apply to everywhere and different sensors” for remote sensing images. This work is based on super-resolution generative adversarial nets (SRGANs), where we modify the loss function and the structure of the network of SRGANs and propose the improved SRGAN (ISRGAN), which makes model training more stable and enhances the generalization ability across locations and sensors. In the experiment, the training and testing data were collected from two sensors (Landsat 8 OLI and Chinese GF 1) from different locations (Guangdong and Xinjiang in China). For the cross-location test, the model was trained in Guangdong with the Chinese GF 1 (8 m) data to be tested with the GF 1 data in Xinjiang. For the cross-sensor test, the same model training in Guangdong with GF 1 was tested in Landsat 8 OLI images in Xinjiang. The proposed method was compared with the neighbor-embedding (NE) method, the sparse representation method (SCSR), and the SRGAN. The peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) were chosen for the quantitive assessment. The results showed that the ISRGAN is superior to the NE (PSNR: 30.999, SSIM: 0.944) and SCSR (PSNR: 29.423, SSIM: 0.876) methods, and the SRGAN (PSNR: 31.378, SSIM: 0.952), with the PSNR = 35.816 and SSIM = 0.988 in the cross-location test. A similar result was seen in the cross-sensor test. The ISRGAN had the best result (PSNR: 38.092, SSIM: 0.988) compared to the NE (PSNR: 35.000, SSIM: 0.982) and SCSR (PSNR: 33.639, SSIM: 0.965) methods, and the SRGAN (PSNR: 32.820, SSIM: 0.949). Meanwhile, we also tested the accuracy improvement for land cover classification before and after super-resolution by the ISRGAN. The results show that the accuracy of land cover classification after super-resolution was significantly improved, in particular, the impervious surface class (the road and buildings with high-resolution texture) improved by 15%.

This article presents an approach to significantly improve the resolution of a highly-sensitive microwave planar sensor response with a super-resolution generative adversarial network (SRGAN). Three identical complementary split-ring resonators are coupled so that the sensitivity is doubled. This highly-sensitive resonator with a deep transmission zero at 4.7 GHz is deployed to measure minute variations of glucose in interstitial fluid. Measuring the sensor response with 1001 frequency-points allows differentiating 10 glucose samples within the range of 40–400 mg/dL. However, in practical readout systems with limited number of frequency-points (here 28), recognizing the deep zero in the S 21 response lacks precision. Sensor responses (magnitude vs. frequency and phase vs. frequency) are converted into equivalent 2D images (heatmaps: phase vs. frequency with colored pixels as amplitude) to be compatible as SRGAN input. As a result of 8-fold resolution enhancement using SRGAN, the classification accuracy is substantially improved from 62.1% to 93.3%. The proposed passive sensor followed by an SRGAN unit is shown to be practical as a wearable glucose monitoring sensor due to its high-sensitivity and high resolution features in a low-profile design. • Three complementary split-ring resonators coupled to double the sensitivity. • Transmission zero at 4.7 GHz deployed to measure glucose in interstitial fluid. • Sensor response is converted to an image for generative adversarial network input. • The resolution of sensor response is enhanced by 8-fold. • Glucose classification accuracy is substantially improved from 62.1% to 93.3%. [ABSTRACT FROM AUTHOR]