Image Restoration Model Research Articles

A First-Order Image Restoration Model that Promotes Image Contrast Preservation

A First-Order Image Restoration Model that Promotes Image Contrast Preservation

Adaptive regularization parameter for nonconvex TGV based image restoration

Overcoming the staircase effect and simultaneously preserving edge details is an important and challenging issue in image processing. To this aim, this paper investigates the nonconvex total generalized variation regularization model for image restoration. Numerically, a highly efficient alternating direction method of multipliers is constructed to deal with the optimization problem in detail, which closely incorporates the superiorities of iteratively reweighted ℓ1 algorithm and variable splitting technique. The proposed strategy can efficiently achieve image restoration and adaptive parameter estimation by applying Morozov’s discrepancy principle. Furthermore, the convergence property of our novel algorithm with the variable regularization parameter is presented. Finally, numerical simulations concertedly illustrate that our approach outperforms several state-of-the-art regularization models, in terms of reconstruction accuracy and edge-preserving ability.

Objective evaluation of low-light-level image intensifier resolution based on a model of image restoration and an applied model of image filtering

Resolution is one of the most important parameters of low-light-level (LLL) image intensifiers, reflecting the target detection performance of assembled night vision devices under 10−3 to 10−1 lx dark environment. The traditional methods of measuring this parameter are classified into subjective evaluation and objective test. The disadvantages of subjective evaluation are strong subjectivity and low accuracy, while the traditional objective test method shows the weaknesses of excessive human intervention and large time consumption. To address these problems, an objective evaluation method based on a model of image restoration and an applied model of image filtering is proposed, which makes use of the similarity between unit stripe pattern and standard stripe pattern to evaluate the recognizability of unit stripe pattern. Firstly, the region of interest (ROI) is cut out from the original image and preprocessed to acquire the clearer results. Then, a model of image restoration is utilized to recover the stripe information lost in image preprocessing. After that, individual unit images are segmented from ROI, laying the foundation for the calculation of unit stripe definition. To extract recognizable unit images from unit image set, an image filtering model composed of several discernible constraints are presented according to the similarity features between unit stripe pattern and standard stripe pattern. Finally, the definition of unit is represented by the weighted sum of the product of constraint score and proportion of the number of discernable images under the constraint to the total number of images in the unit. With the help of linear fitting algorithm, the resolution of LLL image intensifier is calculated by combining the unit resolution-definition correspondences with the limiting definition. To verify the effectiveness of this method, different types of image tubes are used for experiments, and the subjective evaluation method and the advanced objective evaluation technology are adopted as comparison. The experimental results demonstrate that the evaluation results of this method are in good agreement with the subjective judgment results, and the accuracy is higher, reflecting in the maximum deviation is 2.8 lp/mm. The time efficiency of this method is greatly improved compared with that of traditional objective evaluation method. Moreover, the repeatability experiment results reveal that the stability of this approach is superior to that of the cited techniques, and the maximum deviation of evaluation results is 1.2 lp/mm (the lowest). In general, this method can overcome the shortcomings of traditional subjective and objective evaluation methods, and provide an effective and feasible scheme for the standardized measurement of LLL image intensifier resolution.

Directional TGV-Based Image Restoration under Poisson Noise.

We are interested in the restoration of noisy and blurry images where the texture mainly follows a single direction (i.e., directional images). Problems of this type arise, for example, in microscopy or computed tomography for carbon or glass fibres. In order to deal with these problems, the Directional Total Generalized Variation (DTGV) was developed by Kongskov et al. in 2017 and 2019, in the case of impulse and Gaussian noise. In this article we focus on images corrupted by Poisson noise, extending the DTGV regularization to image restoration models where the data fitting term is the generalized Kullback–Leibler divergence. We also propose a technique for the identification of the main texture direction, which improves upon the techniques used in the aforementioned work about DTGV. We solve the problem by an ADMM algorithm with proven convergence and subproblems that can be solved exactly at a low computational cost. Numerical results on both phantom and real images demonstrate the effectiveness of our approach.

Ultrasonic diagnosis of functional dyspepsia under adaptive partial differential denoising model and its relationship with Helicobacter pylori infection

This work was to study the relationship between functional dyspepsia (FD) and Helicobacter pylori (HP) based on the adaptive partial differential denoising model. The adaptive partial differential denoising model was adopted to analyze the ultrasound images, which was then utilized in the ultrasound diagnosis of FD after its related performance was evaluated. Fifty patients with gastrointestinal disease who came to our hospital were recruited and rolled into group A (HP positive) and group B (HP negative), and the clinical symptoms of the two groups were compared. The results showed that the maximum peak signal-to-noise ratio (PSNR) and the running time based on the adaptive partial differential denoising model were both superior to the total variation image restoration (TV) model, with statistical differences (P < 0.05). The PSNR of the partial differential denoising model was superior to that of the TV model, and the mean square error (MSE) was inferior to that of the TV model, both with considerable differences (P < 0.05). For the ultrasound manifestations of the stomach of FD patients, the number of dysfunctional patients in gastric emptying dyskinesias was the largest, accounting for 38%. The overall symptoms of FD patients and HP-infected patients were more severe than those of uninfected patients, especially the symptom of upper abdominal pain, and that in group A was remarkably higher than that of group B (P < 0.05). In summary, the quality of ultrasound images based on the adaptive partial differential denoising model was ideal, and the edge retention capability was strong. In addition, HP was an important factor in causing FD, among which upper abdominal pain was the most obvious.

A novel non-convex low-rank tensor approximation model for hyperspectral image restoration

Remote sensing hyperspectral images (HSIs) are inevitably corrupted by several types of noise in the process of acquisition and transmission. In this paper, we propose a non-convex low-rank tensor approximation (NonLRTA) model for mixed noise removal, which can estimate the intrinsic structure of the underlying HSI from its noisy observation. The clean HSI component is characterized by the ϵ-norm, which is a non-convex surrogate to Tucker rank. The mixed noise is modeled as the sum of sparse and Gaussian components, which are regularized by the l1-norm and the Frobenius norm, respectively. An efficient augmented Lagrange multiplier (ALM) algorithm is developed to solve the proposed model. Experiments implemented on simulated and real HSIs validate the superiority of the proposed method, as compared to the state-of-the-art matrix-based and tensor-based methods.

Existence and Uniqueness of Weak Solutions for a New Class of Convex Optimization Problems Related to Image Analysis

This paper proposes a new anisotropic diffusion model in image restoration that is understood from a variational optimization of an energy functional. Initially, a family of new diffusion functions based on cubic Hermite spline is provided for optimal image denoising. After that, the existence and uniqueness of weak solutions for the corresponding Euler–Lagrange equation are proven in an appropriate functional space, and a consistent and stable numerical model is also shown. We complement this work by illustrating some experiments on different actual brain Magnetic Resonance Imaging (MRI) scans, showing the proposed model’s impressive results.

Design a model of Image Restoration using AI in Digital Image Processing

Image restoration is the process of obtaining a distorted/noise image and giving an approximate clear image of the original image. False focus, motion blur and noise are forms of distortion. Image restoration can be done by reversing the process called Point Extension Function (PSF). In this process, the blurred image is generated by point source imaging and can be used to restore the image lost due to the blur process. Like to form. Modern artificial intelligence (AI) applied to image processing includes facial recognition, object recognition and detection, video, image action, and visual search. It helps to develop smart applications in digital image processing.

Regularization with multilevel non-stationary tight framelets for image restoration

Variational regularization models are one of the popular and efficient approaches for image restoration. The regularization functional in the model carries prior knowledge about the image to be restored. The prior knowledge, in particular for natural images, are the first-order (i.e. variance in luminance) and second-order (i.e. contrast and texture) information. In this paper, we propose a model for image restoration, using a multilevel non-stationary tight framelet system that can capture the image's first-order and second-order information. We develop an algorithm to solve the proposed model and the numerical experiments show that the model is effective and efficient as compared to other higher-order models.

Image Desaturation for SDO/AIA Using Deep Learning

The Atmospheric Imaging Assembly (AIA) on board the Solar Dynamics Observatory (SDO) (launched in February 2010) provides uninterrupted full-disk solar images over 10 wavebands. In the case of violent solar flares, saturation would happen to SDO/AIA images in their core regions, which leads to signal loss, hindering us to understand physical mechanism behind solar flares. This paper introduces a deep learning based image restoration model which can recover signal of saturation region by referring to other normal/valid region within an image. The proposed model, namely PCGAN, combines partial convolution (PC) and conditional generative adversarial network (GAN). The PC module was originally designed for image inpainting, for repairing images with scratches and holes. In addition, a new comprehensive loss function consists of an adversarial loss, a pixel reconstruction loss, a gradient loss, a perceptual loss, a style loss and a total variation loss. Moreover, for validating the proposed model, a new dataset consisting of paired saturated and normal SDO/AIA images is established. Experimental results demonstrate that the proposed PCGAN can get appealing desaturated solar images with respect to both objective and subjective validations.

Multi-frame image restoration method for novel rotating synthetic aperture imaging system

The novel rotating synthetic aperture (RSA) optical imaging system is an important development direction for future high-resolution optical remote sensing satellites in geostationary orbit. However, owing to the rotating rectangular pupil, the point spread function of the RSA system has an asymmetric spatial distribution, and the images obtained using the primary mirror from different rotation angles have nonuniform blur degradation. Moreover, platform vibration and pupil rotation have coupling effects on the RSA imaging, resulting in further radiometric and geometric quality degradation. To address these problems, the image degradation characteristics are first analyzed according to the imaging mechanism. Then, combined with the theory of mutual information, an image registration method is suggested by introducing the orientation gradient information. From this, a multi-frame image restoration model is proposed based on the directional gradient prior of the RSA system image. From the perspective of interpretation and application, when the aspect ratio is less than 3, the proposed inversion restoration method can achieve a satisfactory processing performance. This work can provide engineering application reference for the future space application of RSA imaging technology.

A support-denoiser-driven framework for single image restoration

Model-based methods have been the powerful strategies for solving a variety of imaging inverse problems. Particularly, the sparsity-enforcing regularization models have been especially widely investigated and adopted over the past decades. Along this research direction, one of the most important topics is the model formulation that is able to incorporate the more suitable image priors. In this paper, we propose a universal and flexible image restoration model that exploits the local sparsity, support and nonlocal denoiser priors simultaneously. While the proposed model is nonconvex as a whole, we show that it can be naturally tackled via a multi-stage convex relaxation procedure based on an extended alternating direction method of multiplier (ADMM) algorithm. Comprehensive numerical experiments demonstrate the effectiveness of our proposed algorithm over many existing state-of-the-art methods, in both objective and perceptual quality.

WELL-POSEDNESS AND NUMERICAL SIMULATIONS OF AN ANISOTROPIC REACTION-DIFFUSION MODEL IN CASE 2D

This paper presents a qualitative study of a nonlinear second-order parabolic problem, endowed with a nonlinearity of cubic type as well as non-homogeneous Cauchy-Neumann boundary conditions. Under certain hypotheses on the input data ($ f(t,x), w(t,x), v_0(x) $), we prove the well-posedness and a priori estimates of a solution in the Sobolev space $ W^{1,2}_p(Q) $, extending the results already proven by other authors. Our mathematical model can be applied in many physical phenomena, such as image processing. Numerical simulations illustrate the effectiveness of the mathematical model in image restoration.

DIP-VBTV: A Color Image Restoration Model Combining a Deep Image Prior and a Vector Bundle Total Variation

In this paper, we introduce a new variational model for color image restoration, called DIP-VBTV, which combines two priors: a deep image prior (DIP), which assumes that the restored image can be generated through a neural network and a Vector Bundle Total Variation (VBTV) which generalizes the Vectorial Total Variation (VTV) on vector bundles. VBTV is determined by a geometric triplet: a Riemannian metric on the base manifold, a covariant derivative and a metric on the vector bundle. Whereas VTV prior encourages the restored images to be piece-wise constant, VBTV prior encourages them to be piece-wise parallel with respect to a covariant derivative. For well-chosen geometric triplets, we show that the minimization of VBTV encourages the solutions of the restoration model to share some visual content with the clean image. Then, we show on experiments that DIP-VBTV benefits from this property by outperforming DIP-VTV and state-of-the-art unsupervised methods, which demonstrates the relevance of combining DIP and VBTV priors.

Block-Attentive Subpixel Prediction Networks for Computationally Efficient Image Restoration

Image restoration based on the Deep Convolutional Neural Network (CNN) based image restoration has demonstrated promising results in many sub-tasks, such as image super-resolution, compression artifacts removal, image denoising, and image enhancement. Compared to many CNN-based high-level vision tasks that predict sparse probabilities of each class, the CNN for image restoration requires dense pixel-level predictions with precise intensity-level values. Therefore, a minimum number of spatial pooling (or down-sampling) operations is required to maintain the image details. Therefore, designing a fast or lightweight model for image restoration is a difficult problem and is even more critical when the spatial resolution of an image becomes larger. In this paper, we propose a family of networks called Subpixel Prediction Networks (SPNs) that predict reshaped and spatially down-sampled block-wise tensors instead of raw images with full resolution. Under this scheme, spatial downsampling decreases the restoration performance less while making the network faster. We propose a novel Subpixel Block Attention (SBA) module that re-calibrates blockwise features to diminish blockwise discontinuity to increase the performance further. The experimental results reveal that these networks demonstrate good trade-offs between speed (number of computations) and restoration performance in the three image restoration tasks: image compression artifacts removal, color image denoising, and image enhancement.

Triply Complementary Priors for Image Restoration.

Recent works that utilized deep models have achieved superior results in various image restoration (IR) applications. Such approach is typically supervised, which requires a corpus of training images with distributions similar to the images to be recovered. On the other hand, the shallow methods, which are usually unsupervised remain promising performance in many inverse problems, e.g., image deblurring and image compressive sensing (CS), as they can effectively leverage nonlocal self-similarity priors of natural images. However, most of such methods are patch-based leading to the restored images with various artifacts due to naive patch aggregation in addition to the slow speed. Using either approach alone usually limits performance and generalizability in IR tasks. In this paper, we propose a joint low-rank and deep (LRD) image model, which contains a pair of triply complementary priors, namely, internal and external, shallow and deep, and non-local and local priors. We then propose a novel hybrid plug-and-play (H-PnP) framework based on the LRD model for IR. Following this, a simple yet effective algorithm is developed to solve the proposed H-PnP based IR problems. Extensive experimental results on several representative IR tasks, including image deblurring, image CS and image deblocking, demonstrate that the proposed H-PnP algorithm achieves favorable performance compared to many popular or state-of-the-art IR methods in terms of both objective and visual perception.

Research and Application of Ancient Chinese Pattern Restoration Based on Deep Convolutional Neural Network

In recent years, deep learning, as a very popular artificial intelligence method, can be said to be a small area in the field of image recognition. It is a type of machine learning, actually derived from artificial neural networks, and is a method used to learn the characteristics of sample data. It is a multilayer network, which can learn the information from the bottom to the top of the image through the multilayer network, so as to extract the characteristics of the sample, and then perform identification and classification. The purpose of deep learning is to make the machine have the same analytical and learning capabilities as the human brain. The ability of deep learning in data processing (including images) is unmatched by other methods, and its achievements in recent years have left other methods behind. This article comprehensively reviews the application research progress of deep convolutional neural networks in ancient Chinese pattern restoration and mainly focuses on the research based on deep convolutional neural networks. The main tasks are as follows: (1) a detailed and comprehensive introduction to the basic knowledge of deep convolutional neural and a summary of related algorithms along the three directions of text preprocessing, learning, and neural networks are provided. This article focuses on the related mechanism of traditional pattern repair based on deep convolutional neural network and analyzes the key structure and principle. (2) Research on image restoration models based on deep convolutional networks and adversarial neural networks is carried out. The model is mainly composed of four parts, namely, information masking, feature extraction, generating network, and discriminant network. The main functions of each part are independent and interdependent. (3) The method based on the deep convolutional neural network and the other two methods are tested on the same part of the Qinghai traditional embroidery image data set. From the final evaluation index of the experiment, the method in this paper has better evaluation index than the traditional image restoration method based on samples and the image restoration method based on deep learning. In addition, from the actual image restoration effect, the method in this paper has a better image restoration effect than the other two methods, and the restoration results produced are more in line with the habit of human observation with the naked eye.

An Advanced Methodology of Visibility Used for Underwater Image Enhancement

This paper concentrates towards submerged processing of image so as to improve the picture quality. As the greater part of the pictures of seaward establishments, drinking water store and so forth are caught and examined physically by divers. And manual intervention in this regard is dangerous, costly, and time-consuming and yet does not often enable a full assessment. Hence camera based inspection is used to capture the images under water. Using cameras underwater poses major technological challenges. The objects in the submerged images are pale, difficult to sight and examine because the images of such environment loses the details of the object. The articles in the submerged pictures are swoon, hard to see and examine in light of the fact that the pictures of such condition loses the subtleties of the item. The submerged pictures typically experience the ill effects of non-uniform lighting, low difference, slant, obscures and lessened hues. Also, consequently in this examination work, a novel technique has been proposed for dealing with submerged picture slanting and obscuring if there should be an occurrence of unidirectional cyclic waves and roundabout waves to upgrade the perceivability of submerged pictures. The proposed work develops a geometrical model for image restoration from these distortions with good accuracy

Sequential Gating Ensemble Network for Noise Robust Multiscale Face Restoration.

Face restoration from low resolution and noise is important for applications of face analysis recognition. However, most existing face restoration models omit the multiple scale issues in the face restoration problem, which is still not well solved in the research area. In this paper, we propose a sequential gating ensemble network (SGEN) for a multiscale noise robust face restoration issue. To endow the network with multiscale representation ability, we first employ the principle of ensemble learning for SGEN network architecture design. The SGEN aggregates multilevel base-encoders and base-decoders into the network, which enables the network to contain multiple scales of receptive field. Instead of combining these base-en/decoders directly with nonsequential operations, the SGEN takes base-en/decoders from different levels as sequential data. Specifically, it is visualized that SGEN learns to sequentially extract high-level information from base-encoders in a bottom-up manner and restore low-level information from base-decoders in a top-down manner. Besides, we propose realizing bottom-up and top-down information combination and selection with a sequential gating unit (SGU). The SGU sequentially takes information from two different levels as inputs and decides the output based on one active input. Experimental results on the benchmark dataset demonstrate that our SGEN is more effective at multiscale human face restoration with more image details and less noise than state-of-the-art image restoration models. Further utilizing an adversarial training scheme, SGEN also produces more visually preferred results than other models under subjective evaluation.

RWRM: Residual Wasserstein regularization model for image restoration

&lt;p style='text-indent:20px;'&gt;Existing image restoration methods mostly make full use of various image prior information. However, they rarely exploit the potential of residual histograms, especially their role as ensemble regularization constraint. In this paper, we propose a residual Wasserstein regularization model (RWRM), in which a residual histogram constraint is subtly embedded into a type of variational minimization problems. Specifically, utilizing the Wasserstein distance from the optimal transport theory, this scheme is achieved by enforcing the observed image residual histogram as close as possible to the reference residual histogram. Furthermore, the RWRM unifies the residual Wasserstein regularization and image prior regularization to improve image restoration performance. The robustness of parameter selection in the RWRM makes the proposed algorithms easier to implement. Finally, extensive experiments have confirmed that our RWRM applied to Gaussian denoising and non-blind deconvolution is effective.&lt;/p&gt;