Search

The Intelligent Evaluation System for Calligraphy Characters (IESCC) is used for teaching calligraphy, and users can learn calligraphy through the modifications given by the system. Chinese character skeleton extraction is an important step in the intelligent evaluation algorithm of calligraphic characters. The skeletons of Chinese characters extracted by traditional refinement algorithms are prone to redundant branches and deformed skeletons, which can lead to skeleton extraction results that do not conform to the topology of the original character. In this study, the focus lies on hard‐pen regular script, and skeleton repair and extraction are performed for these characters. According to the writing characteristics of regular script, the redundant burs are removed and the deformation zone of the thinned skeleton is detected, and then the idea of first splitting is used, then restructuring, to propose a skeleton extraction algorithm based on stroke characterization and ambiguous zone detection for hard‐pen regular script, referred to as SCAD. First, a thinning algorithm is used to extract the skeleton of Chinese characters and remove redundant pixels. By analyzing the stroke characteristics of regular script, the burrs are classified and different conditions are set to detect and remove the burrs. Then the ambiguous zones are detected according to the different kinds of junction points. Then, curvature, stroke width and direction deviation are used to analyze the continuity of stroke segments, and the decision function is used to classify the stroke segments. Finally, the stroke segments with optimal pairings were compensated by interpolation according to the direction trend. This concludes the skeleton extraction. Skeleton extraction is performed on 1000 sample characters, and the SCAD algorithm can extract the skeleton of Chinese characters with an accuracy of up to 98.37%. It is proved that the SCAD method proposed here is a practical and effective method to extract the skeleton of hard‐pen regular script. [ABSTRACT FROM AUTHOR]

Despite the existence of various super‐resolution (SR) methods, most of them focus on designing models for specific upscaling factors rather than fully exploiting inter‐scale correlation to improve efficiency. In contrast, multi‐scale SR methods can effectively reduce the redundancy of network parameters by aggregating the feature extraction processes corresponding to multiple scales into a unified process. The aim of this study is to enhance the compactness and efficiency of the SR model. Thus, an efficient multi‐scale SR method called the diverse branch feature refinement network (DBFRN) is proposed. By decoupling the training process and inference process based on the idea of structural re‐parameterization, multi‐branch topology is adopted to enrich multi‐scale learning and merge branches to achieve efficient inference with equivalent effects. Specifically, two re‐parameterization strategies are designed and two corresponding feature refinement blocks for different feature levels in multi‐scale SR network. Extensive experiments demonstrate that the proposed multi‐scale SR method is effective and efficient, and it can outperform advanced single‐scale methods in terms of quantity and quality. [ABSTRACT FROM AUTHOR]

In this paper, we propose a modified general inertial Mann algorithm and prove that it generates a sequence which converges weakly to a fixed point of a nonexpansive mapping in Hilbert spaces. Moreover, by using the viscosity method, we introduce a general inertial viscosity algorithm and prove that it generates a sequence which converges strongly to a common fixed point of a countable family of nonexpansive operators. We also derive schemes for solving constrained convex optimization, monotone inclusion, and nonsmooth convex optimization problems. Finally, we apply one of our proposed algorithms to solve image restoration problem. [ABSTRACT FROM AUTHOR]

In this work, two inertial algorithms for approximating common elements of the sets of solutions of three important problems are constructed. The first problem is a generalized mixed equilibrium one involving relaxed monotone mapping, the second is a zero problem of inverse strongly monotone mappings, while the third one is a fixed point problem of a family of relatively nonexpansive mappings. The first algorithm is a shrinking projection type for a common solution of all the three problems. The second is a generalized Alber projection free method for the second and the third problems. Each of the devised algorithms uses the conjugate gradient-like direction, which allows it to accelerate its iterates toward a solution of the problems. The strong convergence theorem for each of the algorithms is formulated and proved in a real 2 - uniformly convex and uniformly smooth Banach space. Additionally, the applications of our algorithms to convex optimization problems and image recovery problems are studied. The advantages and computational efficiency of our methods are analyzed based on their numerical performance in comparison to some of the existing and recently proposed methods using numerical example. [ABSTRACT FROM AUTHOR]

As an immensely important characteristic of natural images, the nonlocal self-similarity (NSS) prior has demonstrated great promise in a variety of inverse problems. Unfortunately, most current methods utilize either the internal or the external NSS prior learned from the degraded image or training images. The former is inevitably disturbed by degradation, while the latter is not adapted to the image to be restored. To mitigate such problems, this work proposes to learn a hybrid NSS prior from both internal images and external training images and employs it in image restoration tasks. To achieve our aims, we first learn internal and external NSS priors from the measured image and high-quality image sets, respectively. Then, with the learned priors, an efficient method, involving only singular value decomposition (SVD) and a simple weighting method, is developed to learn the HNSS prior for patch groups. Subsequently, taking the learned HNSS prior as the dictionary, we formulate a structural sparse representation model with adaptive regularization parameters called HNSS-SSR for image restoration, and a general and efficient image restoration algorithm is developed via an alternating minimization strategy. The experimental results indicate that the proposed HNSS-SSR-based restoration method exceeds many existing competition algorithms in PSNR and SSIM values. [ABSTRACT FROM AUTHOR]

Recently, convolutional neural networks (CNNs) and vision transformers (ViTs) have emerged as powerful tools for image restoration (IR). Nonetheless, they encountered some limitations due to their characteristics, such as CNNs sacrificing global reception and ViTs requiring large memory and graphics resources. To address these limitations and explore an alternative approach for improved IR performance, we propose two clustering-based frameworks for general IR tasks, which are style-guided context cluster U-Net (SCoC-UNet) and style-guided clustered point interaction U-Net (SCPI-UNet). The SCoC-UNet adopts a U-shaped architecture, comprising position embedding, Encoder, Decoder, and reconstruction block. Specifically, the input low-quality image is viewed as a set of unorganized points, each of which is first given location information by the continuous relative position embedding method. These points are then fed into a symmetric Encoder and Decoder which utilize style-guided context cluster (SCoC) blocks to extract potential context features and high-frequency information. Although SCoC-UNet has obtained decent performance for image restoration, its SCoC block can only capture connectivity at points within the same cluster, which may ignore long-range dependencies in different clusters. To address this issue, we further propose a SCPI-UNet based on SCoC-UNet, which leverages a style-guided clustered point interaction (SCPI) block in place of the SCoC block. The SCPI block utilizes a cross-attention mechanism to establish the connections of feature points between different clusters. Extensive experimental results demonstrate that the proposed SCoC-UNet and SCPI-UNet can handle several typical IR tasks (i.e., JPEG compression artifact reduction, image denoising, and super-resolution) and achieve superior quantitative and qualitative performance over some state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Images are often affected by insufficient illumination and suffer from degradation problems such as low brightness, noise, and color distortion, which results in reduced image quality. Existing low-light image enhancement methods based on Retinex theory decompose images into reflectance and illumination components, which are adjusted separately; however, the intrinsic connection between reflectance and illumination during decomposition is not considered, and multi-scale information during subsequent adjustments is inadequately utilized. In this study, we propose a low-light image enhancement network based on Retinex decomposition and multi-scale adjustment (RDMA), which performs initial decomposition followed by subsequent adjustment. We utilized prior knowledge to design the feature interaction module (FIM) and the feature fusion module (FFM) for image decomposition. Furthermore, a coarse-to-fine multi-scale network with residual channel and spatial attention (RCSA) was designed to remove noise from reflectance, suppress color distortion, preserve image details, and adjust the brightness of illumination. An evaluation of various low-light image datasets and comparisons with state-of-the-art methods showed that the proposed network is superior in terms of enhancement results. [ABSTRACT FROM AUTHOR]

A challenge in image restoration is to recover a clear image from the blurry observation in the presence of different types of noise. There are few works addressing image deblurring under mixed noise. To handle this issue, we propose a general model based on classical wavelet tight frame regularization. We utilize a convexity-preserving term to obtain a component-wise convex model under a mild condition. Indeed, to reduce the cost of solving subproblems, the inexact Gauss–Seidel-based majorized semi-proximal alternating direction method of multipliers (sGS-imsPADMM) with relative error control is developed. Besides, the global convergence of sGS-imsPADMM is demonstrated. Numerical results for the image restoration problems show that the proposed model and solving approach are superior to some state-of-the-art methods both in numerical analysis and visual quality. [ABSTRACT FROM AUTHOR]

This work focuses on recovering images from various forms of corruption, for which a challenging non-smooth, non-convex optimization model is proposed. The model consists of a concave truncated data fidelity functional and a convex total-variational term. We introduce and study various novel equivalent mathematical models from the perspective of duality, leading to two new optimization frameworks in terms of two-stage and single-stage. The two-stage optimization approach follows a classical convex-concave optimization framework with an inner loop of convex optimization and an outer loop of concave optimization. In contrast, the single-stage optimization approach follows the proposed novel convex model, which boils down to the global optimization of all variables simultaneously. Moreover, the key step of both optimization frameworks can be formulated as linearly constrained convex optimization and efficiently solved by the augmented Lagrangian method. For this, two different implementations by projected-gradient and indefinite-linearization are proposed to build up their numerical solvers. The extensive experiments show that the proposed single-stage optimization algorithms, particularly with indefinite linearization implementation, outperform the multi-stage methods in numerical efficiency, stability, and recovery quality. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Xinjiang University (Natural Science Edition) is the property of Xinjiang University 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.)

INTRODUCTION: Criminal activity is expanding exponentially in modern society, which leads towards a great concern about security issues. Facial recognition technology (FRT) is a powerful computer-based system that increasingly being used for recognize and match faces to solve crimes and investigations. OBJECTIVES: Due to poor image clarity and noisy pixels, the detection of criminal faces tends to be inaccurate. Hence, image enhancement techniques are required to recognize criminals with better accuracy. In the proposed model, a multistage progressive V-net based image quality enhancing technique is employed to improve accuracy. METHODS: The Convolutional Neural Network (CNN) for restoring images called MPRV-Net has three stages for a difficult balance between spatial data and highly contextualized information for image restoration tasks while recovering images. RESULTS: For image restoration tasks, including denoising, deblurring, and deraining, MPRV-Net has provided considerable performance benefits on a number of datasets. The suggested network is significant as it eliminates all three types of deviations using a single architecture. The proposed model's performance is tested using performance metrics such as accuracy, precision, recall, and specificity, obtaining 94%, 96%, 93%, and 95%. CONCLUSION: Thus, the proposed Multistage Progressive V-Net model for effectively improves the criminal Facial image for detecting criminals in public places with greater accuracy. [ABSTRACT FROM AUTHOR]

Adverse weather conditions such as rain and haze often lead to a degradation in the quality of maritime images, which is crucial for activities like navigation, fishing, and search and rescue. Therefore, it is of great interest to develop an effective algorithm to recover high-quality maritime images under adverse weather conditions. This paper proposes a prompt-based learning method with degradation perception for maritime image restoration, which contains two key components: a restoration module and a prompting module. The former is employed for image restoration, whereas the latter encodes weather-related degradation-specific information to modulate the restoration module, enhancing the recovery process for improved results. Inspired by the recent trend of prompt learning in artificial intelligence, this paper adopts soft-prompt technology to generate learnable visual prompt parameters for better perceiving the degradation-conditioned cues. Extensive experimental results on several benchmarks show that our approach achieves superior restoration performance in maritime image dehazing and deraining tasks. [ABSTRACT FROM AUTHOR]

In the human–robot collaboration system, the high-precision distortion correction of the camera as an important sensor is a crucial prerequisite for accomplishing the task. The traditional correction process is to calculate the lens distortion with the camera model parameters or separately from the camera model. However, in the optimization process calculate with the camera model parameters, the mutual compensation between the parameters may lead to numerical instability, and the existing distortion correction methods separated from the camera model are difficult to ensure the accuracy of the correction. To address this problem, this study proposes a model-independent lens distortion correction method based on the image center area from the perspective of the actual camera lens distortion principle. The proposed method is based on the idea that the structured image preserves its ratios through perspective transformation, and uses the local image information in the central area of the image to correct the overall image. The experiments are verified from two cases of low distortion and high distortion under simulation and actual experiments. The experimental results show that the accuracy and stability of this method are better than other methods in training and testing results. [ABSTRACT FROM AUTHOR]

Salt and pepper noise is the most dangerous noise which reduces the accuracy of brain diagnosis, and it damages the brain medical MRI images severely, that leads the neurologists to fix incorrect treatments or surgery. The pitfalls raised in the existing denoising methods are less Peak signal-to-noise ratio, high time consumption and incapable for enormous level of noise range. Hence, this research proposes a novel denoising filter which is entitled as 'Decision-based Trimmed Multimode approach oriented Filter (DTMF)' for salt and pepper noise removal. Herein, the noise removal section is branched into six steps which efficiently reduce noises based on the multimode of majority strength. The essential contributions of this approach are (i) designing a rule set for majority strength structured multimode denoising, (ii) computation of majority property oriented parameters like majority-instance, majority strength and majority value, (iii) novel Square shaped Exemplar Modeled Patch Mechanism (SEMPM) to predict noise-free data. The novel SEMPM mechanism grants a solution to the prediction of noise-free pixel in account of the noisy pixels whose surrounding window is completely packed by noisy data. The proposed approach removes the salt and pepper noise with a high Mean structured similarity index measure of 0.881 for a 70% noise range with reasonable time consumption. [ABSTRACT FROM AUTHOR]

This study presents some new iterative algorithms based on the gradient method to solve general constrained systems of conjugate transpose matrix equations for both real and complex matrices. In addition, we analyze the convergence properties of these methods and provide numerical techniques to determine the solutions. The effectiveness of the proposed iterative methods is demonstrated through various numerical examples employed in this study. [ABSTRACT FROM AUTHOR]

While recent years have witnessed the unprecedented success of deep convolutional neural networks (CNNs) and vision transformers in single‐image super‐resolution (SISR), the degradation assumptions are simple and usually bicubic downsampling. Thus, their performances will drop dramatically when the actual degradation does not match this assumption, and they lack the capability to handle multiple degradations (e.g. Gaussian noise, bicubic downsizing, and salt & pepper noise). To address the issues, in this paper, the authors propose a joint SR model (JIRSR) that can effectively handle multiple degradations in a single model. Specifically, the authors build the parallel Transformer and CNN branches that complement each other through bidirectional feature fusion. Moreover, the authors also adopt a random permutation of different kinds of noise and resizing operations to build the training datasets. Extensive experiments on classical SR, denoising, and multiple degradation removal demonstrate that the authors' JIRSR achieves state‐of‐the‐art (SOTA) performance on public benchmarks. Concretely, the authors' JIRSR outperforms the second‐best model by 0.23 to 0.74 dB for multiple degradations removal and is 0.20 to 0.36 dB higher than the SOTA methods on the Urban100 dataset under the ×4 SR task. [ABSTRACT FROM AUTHOR]

Image restoration (IR) attempts to recreate the original (ideal) scene from a degraded observation. The goal of image restoration is to avert the process of image deterioration that happens during image acquisition and processing. Blurring and noise are two common types of picture capture degradation. When the blurring function is unknown, the image restoration issue is referred to as blind image restoration. Existing methods of image restoration do not provide efficient results due to time complexity, computational complexity, large-scale scaling factor and limited input. Therefore, in order to overcome those problems, an Improved Graph Laplacian Regularization with Sparse Coding by integrating Internet of Things (IoT) is developed in this research. The process of removing de-noised portions of image to texture layer and cartoon layer is carried out by Morphological Component Analysis (MCA). An improved Graph Laplacian regularized method and Simultaneous Sparse Coding with Gaussian Scale Mixture (SSC-GSM) methods is performed on texture layer, cartoon layer and restored image. A Levin's dataset and a real-time dataset such as industrial manufacturing products are analyzed in this research. The proposed Graph Laplacian algorithm and sparse coding model are better efficient in identifying sharper texture information and getting a restored image. The proposed method proves that it has better performance in terms of Peak Signal-to-Noise Ratio (PSNR) of 35.82 and Structural Similarity Index Measure (SSIM) of 0.94 than the existing methods. [ABSTRACT FROM AUTHOR]

In this paper, we propose an Efficient Frequency-Guided image deraining transformer, called former, to explore the more useful self-attention values from the frequency domain for better image deraining. Inspired by the traditional convolution theorem, we design frequency domain guidance attention to learn rich global and local dependencies. Firstly, we employ affine coupling to increase receptive fields implicitly, enabling the capturing of multi-scale spatial feature representations, and then they are transferred to the frequency domain using the Fourier transform. Instead of using vanilla attention, we adopt element-wise product to model global frequency information for better feature aggregation and reducing spatial complexity. As traditional feed-forward networks struggle with frequency information, we introduce an adaptive frequency collaborative block to adaptively learn frequency information and integrate local spatial information for improved image restoration. Moreover, a scale feature enhancement block is designed to exchange and aggregate information at different scales for learning mixed features of various scales. Extensive experimental results on commonly used benchmark datasets demonstrate that our method outperforms competitive methods in terms of performance. [ABSTRACT FROM AUTHOR]

This paper proposes an adaptive two-parameter accelerated conjugate gradientmethod, which satisfies the sufficient descent condition in the search direction. The Powell restart strategy is designed in the algorithm to improve its numerical performance. Our proposed method does not add extra computational effort compared to other methods. Furthermore, under general assumptions, we demonstrate the global convergence of our proposed method under theWolfe line search. Finally, we compare with other methods on the unconstrained optimization and image restoration problems. Numerical experiments are presented to show that our proposed method is feasible. [ABSTRACT FROM AUTHOR]

Hazy images suffer from two problems. The low contrast can be enhanced by estimating a transmission layer, and the colour cast can be restored by estimating an airlight. These two variables, together with the albedo layer, are the constitutive elements of a hazy image. The resulting quality of dehazed images is inextricably linked to the accurate estimation of these components. However, it is ill‐posed to decompose these variables from a single image. As such, this paper presents an innovative algorithm intended to facilitate the optimal decomposition of a hazy image. Using the Markov random field model, an optimal framework is established that allows the simultaneous estimation of the three components across the three‐colour channels. To improve the visual quality, three improvements are proposed in the variational solution for the optimal components. The dehazed result is recomposed from the components with the transmission enhanced to circumvent any potential artefacts or information loss. Extensive experiments on natural images corroborate that the proposed algorithm outperforms state‐of‐the‐art dehazing methods, both qualitatively and quantitatively. [ABSTRACT FROM AUTHOR]

Single image dehazing in real scenarios is still a particularly challenging task due to the large domain discrepancy between synthetic and real hazy images. To address this problem, the dual‐route domain‐aware adaptation framework with the bridging domain is proposed. First, inspired by the effective multistage strategy in low‐level tasks, the bridging domain is constructed with the color‐preserved adaptive histogram equalization to facilitate the adaptation and improve the performance of real hazy images. Second, the totally shared structure is relaxed and the residual dual‐path domain‐aware modules (RDDM) for synthetic and the bridging domains are proposed, which facilitates extracting the domain‐specific haze information with the different parameters. Third, a half‐cyclic constraint is proposed for the unsupervised hazy images to avoid structure distortion during the unsupervised adversarial training process. Finally, for convenience in the inference stage, feature enhancement modules (FEM) are proposed for the original real hazy images to learn the pre‐process operation in the training stage. Extensive qualitative and quantitative experiments demonstrate that the proposed method significantly improves the dehazing performance on synthetic and real hazy images. [ABSTRACT FROM AUTHOR]

This paper proposes an image dehazing prior, called Regional Saturation-Value Translation (RSVT), in order to address the color distortion issues produced by prevailing prior-based dehazing methods when processing hazy images with large sky regions. The proposed RSVT prior is derived from statistical analyses of the correlation between hazy points and respective haze-free points in the HSV color space. The prior is based upon two key observations in the sky areas. First, the difference in terms of hue for a pair of hazy and haze-free points is very small, raising an assumption that the variability of pixel values caused by haze mostly occurs in the saturation and value spaces. This leads to the second observation that, in the 2D saturation-value coordinate system, almost all the lines passing through corresponding pairs of hazy-clean points, termed S-V lines, are likely to intersect around the airlight coordinates. A hybrid refined dark channel is introduced in order to decompose the input hazy image into sky and non-sky regions and to estimate the global atmospheric light. Combining the prior with the hybrid refined dark channel, a novel single image dehazing framework is proposed. Haze removal is performed separately for the sky and non-sky regions by adopting the proposed RSVT prior and Koschmieder's law, respectively. The experimental results have shown that the proposed dehazing method can restore visually compelling sky color and effectively handle the color distortion issues associated with large sky regions. [ABSTRACT FROM AUTHOR]

In existing highlight removal methods, research on highlights on metal surfaces is relatively limited. Therefore, this paper proposes a new, simple, effective method for removing highlights from metal surfaces, which can better restore image details. Additionally, the approach presented in this paper is highly effective for highlight removal in everyday real-world highlight scenarios. Specifically, we first separate the image's illumination space based on the Retinex model and generate a highlight mask using the mean plus standard deviation method. Then, based on the mask, we transform the original image and the image at the corresponding mask position to the V channel of the HSV space, achieving the effective elimination of highlights. To enhance the details of the restored image, this paper introduces a method involving adaptive Laplacian sharpening operators and gradient fusion for detail enhancement at highlight removal positions. Finally, a highlight-free image with well-preserved details is obtained. In the experimental phase, we validate the proposed method using real welding seam highlight datasets and real-world highlight datasets. Compared with the existing methods, the proposed method achieves high-quality qualitative and quantitative evaluation. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new modification of a three-term derivative-free projection algorithm for solving a system of monotone nonlinear equations. The global convergence was proved under some suitable conditions, and the search direction of the proposed algorithm satisfies the sufficient descent property. Numerical computations were presented to display the efficacy of the proposed algorithm compared to some existing algorithms. Moreover, the proposed algorithm is applied to solve problems of image recovery. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicle (UAV)-based geological mapping is significant for understanding the geological structure in the high-steep slopes, but the images obtained in these areas are inevitably influenced by the backlit effect because of the undulating terrain and the viewpoint change of the camera mounted on the UAV. To handle this concern, a novel backlit image restoration method is proposed that takes the real-world application into account and addresses the color distortion issue existing in backlit images captured in high-steep slope scenes. Specifically, there are two main steps in the proposed method, which consist of the backlit removal and the color and detail enhancement. The backlit removal first eliminates the backlit effect using the Retinex strategy, and then the color and detail enhancement step improves the image color and sharpness. The author designs extensive comparison experiments from multiple angles and applies the proposed method to different engineering applications. The experimental results show that the proposed method has potential compared to other main-stream methods both in qualitative visual effects and universal quantitative evaluation metrics. The backlit images processed by the proposed method are significantly improved by the process of feature key point matching, which is very conducive to the fine construction of 3D geological models of the high-steep slope. [ABSTRACT FROM AUTHOR]

Recent years of object detection (OD), a fundamental task in computer vision, have witnessed the rise of numerous practical applications of this sub-field such as face detection, self-driving, security, and more. Although existing deep learning models show significant achievement in object detection, they are usually tested on datasets having mostly clean images. Thus, their performance levels were not measured on degraded images. In addition, images and videos in real-world scenarios often involve several natural artifacts such as noise, haze, rain, dust, and motion blur due to several factors such as insufficient light, atmospheric scattering, and faults in image sensors. This image acquisition-related problem becomes more severe when it comes to detecting small objects in aerial images. In this study, we investigate the small object identification performance of several state-of-the-art object detection models (Yolo 6/7/8) under three conditions (noisy, motion blurred, and rainy). Through this inspection, we evaluate the contribution of an image enhancement scheme so-called MPRNet. For this aim, we trained three OD algorithms with the original clean images of the VisDrone dataset. Followingly, we measured the detection performance of saved YOLO models against (1) clean, (2) degraded, and (3) enhanced counterparts. According to the results, MPRNet-based image enhancement promisingly contributes to the detection performance and YOLO8 outperforms its predecessors. We believe that this work presents useful findings for researchers studying aerial image-based vision tasks, especially under extreme weather and image acquisition conditions [ABSTRACT FROM AUTHOR]

Image restoration aims to reconstruct a latent high-quality image from a degraded observation. Recently, the usage of Transformer has significantly advanced the state-of-the-art performance of various image restoration tasks due to its powerful ability to model long-range dependencies. However, the quadratic complexity of self-attention hinders practical applications. Moreover, sufficiently leveraging the huge spectral disparity between clean and degraded image pairs can also be conducive to image restoration. In this paper, we develop a dual-domain strip attention mechanism for image restoration by enhancing representation learning, which consists of spatial and frequency strip attention units. Specifically, the spatial strip attention unit harvests the contextual information for each pixel from its adjacent locations in the same row or column under the guidance of the learned weights via a simple convolutional branch. In addition, the frequency strip attention unit refines features in the spectral domain via frequency separation and modulation, which is implemented by simple pooling techniques. Furthermore, we apply different strip sizes for enhancing multi-scale learning, which is beneficial for handling degradations of various sizes. By employing the dual-domain attention units in different directions, each pixel can implicitly perceive information from an expanded region. Taken together, the proposed dual-domain strip attention network (DSANet) achieves state-of-the-art performance on 12 different datasets for four image restoration tasks, including image dehazing, image desnowing, image denoising, and image defocus deblurring. The code and models are available at https://github.com/c-yn/DSANet. [ABSTRACT FROM AUTHOR]

The main objective of blind image deblurring is to restore a high-quality sharp image from a blurry input through estimation of unknown blur kernel and latent sharp image. This is an ill posed problem as a range of additional heuristics are required to accurately estimate the blur kernel. These methods have a major drawback that estimated kernel doesn't result in minimum cost function for truly sharp image. In this paper, an improved blind image deblurring approach named Scharr Edge-based regularization (SEBR) based on combination of state-of-the-art Scharr edge based (SEB) gradient operator and a normalized regularization is proposed that accurately estimates the blur kernel and provides minimum cost function for sharp images. Initially, the SEB operator is applied to blurry input to preserve the spatial relations between the initial pixel values of the image. Moreover, the isotropic nature of the Scharr operator ensures the rotation symmetry effectively while optimizing the localization of salient edges to produce a gradient image. Finally, after applying normalized regularization, the blur kernel is estimated with high precision, which then recovers a sharp image. Experimental evaluations are performed on publicly available datasets of synthetic and real blur data. The proposed SEBR algorithm is very fast and robust in nature. The experimental result on synthetic data shows that SEBR improves the values of PSNR and SSIM. The SEBR also achieves favorable results in terms of visual quality against state-of-the-art deblurring techniques on real blur images having complex backgrounds with uniform and non-uniform blur, and images taken in low lighting conditions. [ABSTRACT FROM AUTHOR]

Maintaining image fidelity during transmission is challenging for live optical quantum image transmission. This paper introduces a novel "Quantum-Inspired Adaptive Loss Detection and Real-time Image Restoration" approach. The method incorporates adaptive loss detection and real-time restoration techniques, drawing inspiration from quantum principles to model the optical quantum environment. The core innovation is a near-to-far continuous approach adapted to the quantum environment's dynamics, enhancing image clarity and quality. A Network-in-Network architecture with MLPConv layers is proposed for the system model to estimate the transmission map for image de-hazing using the Reinforcement Learning system (ID-RL). A depth-aware dehazing reinforcement learning framework tackles image regions separately. Experiments demonstrate superior over prior SSIM and PSNR arts, even with minimal training data. Efficiency for real-time usage is shown, with potential for autonomous surveillance applications in smart cities. This quantum-inspired adaptive technique is a promising advancement for live optical quantum image transmission fidelity. [ABSTRACT FROM AUTHOR]

We present a highly effective algorithm for image dehazing that leverages the valuable information within the hazy image to guide the haze removal process. Our proposed algorithm begins by employing a neural network that has been trained to establish a mapping between hazy images and their corresponding clear versions. This network learns to identify the shared structural elements and patterns between hazy and clear images through the training process. To enhance the utilization of guidance information from the generated reference image, we introduce a progressive feature fusion module that combines the features extracted from the hazy image and the reference image. Our proposed algorithm is an effective solution for image dehazing, as it capitalizes on the guidance information in the hazy appearance. By combining the strengths of deep learning, progressive feature fusion, and end-to-end training, we achieve impressive results in restoring clear images from hazy counterparts. The practical applicability of our algorithm is further validated by its success on benchmark data sets and real-world SEM and TEM images. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Jilin University (Science Edition) / Jilin Daxue Xuebao (Lixue Ban) is the property of Zhongguo Xue shu qi Kan (Guang Pan Ban) Dian zi Za zhi She 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.)

Copyright of Journal of South China University of Technology (Natural Science Edition) is the property of South China University of Technology 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.)

Separable nonlinear least squares (SNLLS) problems are critical in various research and application fields, such as image restoration, machine learning, and system identification. Solving such problems presents a challenge due to their nonlinearity. The traditional gradient iterative algorithm often zigzags towards the optimal solution and is sensitive to the initial guesses of unknown parameters. In this paper, we improve the convergence rate of the traditional gradient method by implementing a multi-step-length gradient iterative algorithm. Moreover, we incorporate the variable projection (VP) strategy, taking advantage of the separable structure observed in SNLLS problems. We propose a multi-step-length gradient iterative-based VP (Mul-GI-VP) method to solve such nonlinear optimization problems. Our simulation results verify the feasibility and high efficiency of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The global semantics and the local scene representation are crucial for image restoration. Although existing methods have proposed various hybrid frameworks of convolutional neural networks (CNNs) and Transformers to take into account both, they only focus on the complementarity of their capabilities. On the one hand, these works neglect the mutual guiding role of the two information, and on the other hand, they also ignore that the semantic gap caused by the two different modeling systems of convolution and Self-Attention seriously impede the feature fusion. In this work, we propose to establish entanglement between the global and the local to bridge the semantic gap and achieve mutual-guided modeling of the two features. In the proposed hybrid framework, the modeling of convolution and Self-Attention is no longer independent of each other, but through the proposed Mutual Transposed Cross Attention (MTCA), the mutual dependence of the two is realized, thereby strengthening the joint modeling of local and global. Further, we propose Bidirectional Injection Module (BIM), which makes the global and local features adapt to each other in parallel before fusion and greatly reduces interference in the fusion process caused by semantic gap. The proposed method is qualitatively and quantitatively evaluated on multiple benchmark datasets, and extensive experiments show that our method reaches the state-of-the-art with low computational consumption. [ABSTRACT FROM AUTHOR]

In recent years, there has been a growing interest in the use of Generative Adversarial Networks (GANs). Thanks to their outstanding performance in image translation and generation, they play an increasingly important role in computer vision applications. Most approaches based on GAN focus on proposing task-specific auxiliary modules or loss functions that are tailored to address various challenges of a single application, but often do not perform better when evaluated to improve other image generation tasks. Moreover, the basic ResNet and U-Net based GAN generators reach their limits in many image restoration and enhancement use cases. Therefore, in this paper, we propose a generic GAN referred to as Multi-Kernel Filter-based Conditional Generative Adversarial Network (MFGAN). We develop a new GAN generator with multiple CNN streams to extract more relevant and discriminative features related to the studied task. The proposed MFNet generator consists of two CNN modules, feature extraction and feature compression, which are combined to connect both the GAN encoder and decoder. It considers the strengths of conventional layers at different scale levels with multi-kernel filtering to capture high to low feature frequencies that reflect the complex image degradations and structural image details. Extensive experiments on five challenging applications for image enhancement, image restoration, and infrared image translation demonstrate the superiority and effectiveness of the proposed MFGAN in removing image degradation and generating visually appealing fake images. Our MFGAN quantitatively outperforms both state-of-the-art GANs and other CNN-based architectures in all tested benchmarks. [ABSTRACT FROM AUTHOR]

Copyright of Jordanian Journal of Computers & Information Technology is the property of Jordanian Journal of Computers & Information Technology 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.)

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. 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.)

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. 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.)

Deep learning offers promise in enhancing low‐quality images by addressing weak fluorescence signals, especially in deep in vivo mouse brain imaging. However, current methods struggle with photon scarcity and noise within in vivo deep mouse brains, and often neglecting tissue preservation. In this study, we propose an innovative in vivo cortical fluorescence image restoration approach, combining signal enhancement, denoising, and inpainting. We curated a deep brain cortical image dataset and developed a novel deep brain coordinate attention restoration network (DeepCAR), integrating coordinate attention with optimized residual networks. Our method swiftly and accurately restores deep cortex images exceeding 800 μm, preserving small‐scale tissue structures. It boosts the peak signal‐to‐noise ratio (PSNR) by 6.94 dB for weak signals and 11.22 dB for large noisy images. Crucially, we validate the effectiveness on external datasets with diverse noise distributions, structural features compared to those in our training data, showcasing real‐time high‐performance image restoration capabilities. [ABSTRACT FROM AUTHOR]

Defocus blurring imaging seriously affects the observation accuracy and application range of optical microscopes, and the blurring kernel function is a key parameter for high-resolution image restoration. However, its solving process is complicated and high in computational cost. Image restoration based on most neural networks has high requirements on data sets and the image resolution after restoration is limited because of the lack of quantitative estimation of blurring kernels. In this study, an image restoration method guided by blurring kernel estimation for microscopic defocused images is proposed. First, to reduce the blurring kernel estimation error caused by the positive and negative difference in microscopic defocused imaging, a defocused image classification network is designed to classify the input defocused images with different defocus distances and directions, and its output images are input into the blurring kernel extraction network composed of the feature extraction, correlation, and blurring kernel reconstruction layers. Second, a non-blind defocused image restoration model to restore the high-resolution images is proposed by introducing the blurring kernel extraction module into the restoration network based on U-Net, and the blurring kernel estimation and image restoration losses are jointly trained to realize image restoration guided by blurring kernel estimation. Finally, the experimental results of our proposed method demonstrate significant improvements in both the peak signal-to-noise ratio and structural similarity index measure when compared to other methods.

Ring-array photoacoustic tomography (PAT) system has been widely used in noninvasive biomedical imaging. However, the reconstructed image usually suffers from spatially rotational blur and streak artifacts due to the non-ideal imaging conditions. To improve the reconstructed image towards higher quality, we propose a concept of spatially rotational convolution to formulate the image blur process, then we build a regularized restoration problem model accordingly and design an alternating minimization algorithm which is called blind spatially rotational deconvolution to achieve the restored image. Besides, we also present an image preprocessing method based on the proposed algorithm to remove the streak artifacts. We take experiments on phantoms and in vivo biological tissues for evaluation, the results show that our approach can significantly enhance the resolution of the image obtained from ring-array PAT system and remove the streak artifacts effectively.

Fundus cameras are widely used by ophthalmologists for monitoring and diagnosing retinal pathologies. Unfortunately, no optical system is perfect, and the visibility of retinal images can be greatly degraded due to the presence of problematic illumination, intraocular scattering, or blurriness caused by sudden movements. To improve image quality, different retinal image restoration/enhancement techniques have been developed, which play an important role in improving the performance of various clinical and computer-assisted applications. This paper gives a comprehensive review of these restoration/enhancement techniques, discusses their underlying mathematical models, and shows how they may be effectively applied in real-life practice to increase the visual quality of retinal images for potential clinical applications including diagnosis and retinal structure recognition. All three main topics of retinal image restoration/enhancement techniques, i.e., illumination correction, dehazing, and deblurring, are addressed. Finally, some considerations about challenges and the future scope of retinal image restoration/enhancement techniques will be discussed.

Abstract In the field of meteorology, the global radar network is indispensable for detecting weather phenomena and offering early warning services. Nevertheless, radar data frequently exhibit anomalies, including gaps and clutter, arising from atmospheric refraction, equipment malfunctions, and other factors, resulting in diminished data quality. Traditional radar blockage correction methods, such as employing approximate radial information interpolation and supplementing missing data, often fail to effectively exploit potential patterns in massive radar data, for the large volume of data precludes a thorough analysis and understanding of the inherent complex patterns and dependencies through simple interpolation or supplementation techniques. Fortunately, edge computing possesses certain data processing capabilities and cloud center boasts substantial computational power, which together can collaboratively offer timely computation and storage for the correction of radar beam blockage. To this end, an edge-cloud collaborative driven deep learning model named DenMerD is proposed in this paper, which includes dense connection module and merge distribution (MD) unit. Compared to existing models such as RC-FCN, DenseNet, and VGG, this model greatly improves key performance metrics, with 30.7 $$\%$$ % improvement in Critical Success Index (CSI), 30.1 $$\%$$ % improvement in Probability of Detection (POD), and 3.1 $$\%$$ % improvement in False Alarm Rate (FAR). It also performs well in the Structure Similarity Index Measure (SSIM) metrics compared to its counterparts. These findings underscore the efficacy of the design in improving feature propagation and beam blockage accuracy, and also highlights the potential and value of mobile edge computing in processing large-scale meteorological data.

Abstract Shadow removal is a challenging task because the variety of shadows is influenced by surface texture and lighting. This paper proposes a dynamic alignment and illumination‐aware convolution (DAIC), which consists of a Feature Alignment Module (FAM) and a Dynamic Weight Module (DWM). FAM aligns the downsampled deep features with the original features and helps to extract the optimal local information to ensure that the object texture features are not corrupted. DWM generates weights according to different lighting variations for a better shadow removal result. The shadow removal approach is based on an image decomposition algorithm using a multi‐exposure image fusion model. Here, the shadow removal network and refinement network use U‐Net framework, and the transposed convolution operations are replaced with DAIC in the decoder part of U‐Net to improve the performance of the network. The experiments are conducted on two large shadow removal datasets, ISTD+ and SRD. Compared to state‐of‐the‐art methods, this model achieves optimal performance in terms of Root Mean Square Error (RMSE) for the non‐shadow region. It also achieves performance comparable to the state‐of‐the‐art method in terms of RMSE for the shadow region and structural similarity index measurement for the entire image.

Abstract Light undergoes attenuation due to scattering and refraction when propagating through aerosols. In foggy conditions, Aerosol particles in the troposphere exhibit high mobility introducing intricate non‐linear noise into images. Foggy image restoration represents an ill‐posed problem, where traditional physical models and image enhancement techniques often prove inadequate in delivering effective solutions. This paper introduces a novel deep sub‐pixel reconstruction algorithm for foggy image restoration, pioneering the application of sub‐pixel reconstruction modules to this domain. This model employs convolutional layers to extract low‐level features and dense‐connected layers for high‐level feature extraction. Furthermore, a specialized sub‐pixel reconstruction module tailored for the task of foggy image restoration is designed, with the purpose of reconstructing dehazed images from latent vectors. During training, a generative adversarial training framework is adopted, incorporating a purpose‐designed discriminator. Additionally, a fusion loss is implemented to facilitate model refinement. Quantitative and qualitative evaluation experiments conducted on synthetic and real‐world image datasets demonstrate the effectiveness of the proposed method in preserving finer details. The Structural Similarity Index (SSIM) is observed to improve by 2.5%, attesting to enhanced perceptual quality for grayscale foggy images.

Abstract Image restoration, as a fundamental research topic of image processing, is to reconstruct the original image from degraded signal using the prior knowledge of image. Group sparse representation (GSR) is powerful for image restoration; it however often leads to undesirable sparse solutions in practice. In order to improve the quality of image restoration based on GSR, the sparsity residual model expects the representation learned from degraded images to be as close as possible to the true representation. In this article, a group residual learning based on low‐rank self‐representation is proposed to automatically estimate the true group sparse representation. It makes full use of the relation among patches and explores the subgroup structures within the same group, which makes the sparse residual model have better interpretation furthermore, results in high‐quality restored images. Extensive experimental results on two typical image restoration tasks (image denoising and deblocking) demonstrate that the proposed algorithm outperforms many other popular or state‐of‐the‐art image restoration methods.

Abstract Image inpainting networks based on deep learning techniques have been widely used in many important fields. However, most inpainting networks fail to generate desirable repaired images. This may be due to their failure to extract effective features and accurately assign high weights to the undamaged regions. To alleviate these problems, an image inpainting network based on gated convolution and multi‐level attention mechanism (IIN‐GCMAM) is proposed in this paper. This network follows encoder–decoder architecture, consisting of the gated convolution encoder (GC‐encoder) and the multi‐level attention mechanism decoder (MAM‐decoder). The GC‐encoder weighs the extracted features with gated convolutions, which reduces the interference caused by the damaged regions. The multi‐level attention mechanism employed in the MAM‐decoder uses multi‐scale feature maps spatially and channel‐wise to improve the consistency in global structure and the fineness of repaired results. Extensive experiments are conducted on the common datasets, Paris StreetView and CelebA. Experimental results indicate that the proposed IIN‐GCMAM can achieve a good performance on the common evaluation metrics and visual effects. It can achieve 0.0408, 0.720, and 22.27 in MAE, SSIM, and PSNR at the mask ratio of 50%–60%, respectively.

Non-uniform deblurring is one of the most important image restoration tasks for providing appropriate information for subsequent applications that require image recognition. Conventional deep learning-based multi-frame deblurring methods collectively handle many types of non-uniform blurring, such as camera shakes and motion blur. However, edge and high-frequency component restoration is still insufficient for severe motion blur. This paper proposes an auxiliary edge-enhanced branch to support motion blur restoration for deep learning-based multi-frame deblurring methods. The background region in an image with little motion generally has more edge information, whereas the moving object region lacks high-frequency components. Thus, we propose a motion orthogonal edge (MOE) feature that extracts only the edge information of moving objects by computing the pixel-wise inner product between the edge information obtained by Sobel filters and the optical flow representing motion in the image. MOEs can emphasize only the edges of moving objects excluding the backgrounds. In this paper, we add an edge-enhanced branch that computes MOEs to a conventional multi-frame deblurring method, the spatio-temporal deformable attention network, and call it ESTDANet. We introduce additional frequency reconstruction loss to restore high-frequency components and compare our proposed ESTDANet with the conventional baseline method in our comparative experiments. Furthermore, we introduce motion-weighted SSIM maps to distinguish the deblurring accuracy in motion regions spatially. The results show that our edge-enhanced branch aids edge restoration in the motion deblurring of conventional methods.

Optical synthetic aperture imaging (OSAI) systems consist of multiple subapertures arranged in a specific spatial pattern to achieve high resolution imaging comparable to that of a large aperture while reducing costs. However, due to the sparsity of the apertures and co-phase errors, these systems inevitably suffer from image degradation and blurring. Traditional nonblind deconvolution methods are commonly used for image deblurring in OSAI systems, but they require accurate prior knowledge, which, if inaccurate, can affect image restoration quality. Recent deep learning-based methods have achieved remarkable results, but they do not consider the impact of co-phase errors in OSAI systems and require large amounts of real datasets for training. This study proposes a semiblind unsupervised learning method named RPIR for image restoration in OSAI systems with co-phase errors. RPIR is based on the traditional maximum a posteriori (MAP) model and utilizes a multiscale neural network that does not require training to capture the input blur kernel errors, which are then used as the residual prior term of the MAP model. The data term and the prior term are solved using an alternating minimization algorithm. Consequently, RPIR can effectively address the issue of inaccurate blur kernels caused by variations in co-phase errors in OSAI systems. Experimental results demonstrate that RPIR significantly improves image resolution and detail clarity in OSAI systems with complex co-phase errors, outperforming traditional deconvolution methods and other unsupervised deep learning methods.

With the rapid development of the economy, the aspirations for spiritual fulfillment have transcended material demands, fostering a greater appreciation for artistic lifestyles. Artistic design works, embodying humanity’s interactions with nature and itself in daily life, interpret people’s comprehension and pursuit of beauty through diverse forms of expression. The precise restoration, preservation of artistic value, and conservation of these works are paramount for historical research, cultural transmission, and the perpetuation of artistic legacies. This paper proposes an image restoration algorithm for artistic design works utilizing machine learning, aiming to establish an appreciation system for such works. By leveraging advanced machine learning techniques, the system facilitates efficient restoration and digital appreciation of artistic design works, enhancing restoration quality and broadening artistic appreciation horizons. Through the implementation of this system, it is envisioned that artistic design works will be better preserved and transmitted, enabling individuals to appreciate the grandeur of art.