Restoration Algorithm Research Articles

UID2021: An Underwater Image Dataset for Evaluation of No-Reference Quality Assessment Metrics

Achieving subjective and objective quality assessment of underwater images is of high significance in underwater visual perception and image/video processing. However, the development of underwater image quality assessment (UIQA) is limited for the lack of publicly available underwater image datasets with human subjective scores and reliable objective UIQA metrics. To address this issue, we establish a large-scale underwater image dataset, dubbed UID2021, for evaluating no-reference (NR) UIQA metrics. The constructed dataset contains 60 multiply degraded underwater images collected from various sources, covering six common underwater scenes (i.e., bluish scene, blue-green scene, greenish scene, hazy scene, low-light scene, and turbid scene), and their corresponding 900 quality improved versions are generated by employing 15 state-of-the-art underwater image enhancement and restoration algorithms. Mean opinion scores with 52 observers for each image of UID2021 are also obtained by using the pairwise comparison sorting method. Both in-air and underwater-specific NR IQA algorithms are tested on our constructed dataset to fairly compare their performance and analyze their strengths and weaknesses. Our proposed UID2021 dataset enables ones to evaluate NR UIQA algorithms comprehensively and paves the way for further research on UIQA. The dataset is available at https://github.com/Hou-Guojia/UID2021 .

A novel bio-inspired optimization algorithm for medical image restoration using Enhanced Regularized Inverse Filtering

A novel bio-inspired optimization algorithm for medical image restoration using Enhanced Regularized Inverse Filtering

High-speed and high-resolution YAG fiber based distributed high temperature sensing system empowered by a 2D image restoration algorithm.

High temperature monitoring is critical to the health and performance of vital pieces of infrastructure such as jet engine, fuel cells, coal gasifiers, and nuclear reactor core. However, it remains a big challenge to realize reliable distributed high temperature sensing system with high speed, high spatial and temperature resolution simultaneously. In this work, a Raman distributed high temperature sensing system with high temperature resolution and high spatial resolution was realized in a single-crystal YAG fiber. The sensing system demonstrated operation from room temperature up to 1400°C with a spatial resolution of 7 cm and response time of 1 millisecond in a 1m long YAG fiber. The average temperature sensitivity of the system is about 7.95 × 10-4/°C. To the best of our knowledge, this is the best spatial resolution and response time reported in literature. In this system, a 2D image restoration was used to boost the signal to noise ratio of sensor. Empowered by the algorithm, the average temperature standard deviation along the sensing fiber of 7.89 °C was obtained based on a single frame data in 1 millisecond. A new record of temperature resolution of 0.62 °C was demonstrated in only 1 second frame data traces, which enables a fast response capacity.

End-to-end learned single lens design using improved Wiener deconvolution.

End-to-end single-lens imaging system design is a method to optimize both optical system and reconstruction algorithm. Most end-to-end single lens systems use convolutional neural networks (CNN) for image restoration, which fit the transformation relationship between the aberrated image and the ground truth image in the training set. Based on the principle of optical imaging, we realize non-blind image restoration through Wiener deconvolution. Wiener deconvolution is improved with the powerful fitting ability of depth learning so that the noise parameters and the blur kernel in Wiener deconvolution can be simultaneously optimized with the optical parameters in the lens. Extensive comparative tests have been conducted to demonstrate the single-lens imaging system obtained by our method has more stable imaging quality and a 40 times greater imaging speed than the method using CNN restoration algorithm.

Panoramic annular image restoration algorithm by prediction based on the lens design characteristics.

A panoramic annular lens optical system is important in circumferential detection. However, a panoramic annular image (PAI) has severe tangential and radial distortion. This study proposes a 3σ guideline-based method, which determines the unwrapping center point of the PAI, and a prediction method based on the lens design characteristics according to the intrinsic distortion of the PAL to correct, respectively, the tangential distortion and the radial distortion. The proposed methods can ensure the restoration ability and simplify the dependence on experimental conditions. The experimental results confirm the effectiveness of the proposed method, thus enabling future panoramic optical image detection.

Signal restoration algorithm for photoacoustic imaging systems.

In a photoacoustic (PA) imaging system, the detectors are bandwidth-limited. Therefore, they capture PA signals with some unwanted ripples. This limitation degrades the resolution/contrast and induces sidelobes and artifacts in the reconstructed images along the axial direction. To compensate for the limited bandwidth effect, we present a PA signal restoration algorithm, where a mask is designed to extract the signals at the absorber positions and remove the unwanted ripples. This restoration improves the axial resolution and contrast in the reconstructed image. The restored PA signals can be considered as the input of the conventional reconstruction algorithms (e.g., Delay-and-sum (DAS) and Delay-multiply-and-sum (DMAS)). To compare the performance of the proposed method, DAS and DMAS reconstruction algorithms were performed with both the initial and restored PA signals on numerical and experimental studies (numerical targets, tungsten wires, and human forearm). The results show that, compared with the initial PA signals, the restored PA signals can improve the axial resolution and contrast by 45% and 16.1 dB, respectively, and suppress background artifacts by 80%.

Rank minimization via adaptive hybrid norm for image restoration

Rank minimization methods have achieved promising performance in various image processing tasks. However, there are still two challenging problems in the existing works. One is that most of the current methods only regularize singular values by using a single l1-norm, such as the well-known nuclear norm minimization (NNM) and the weighted nuclear norm minimization (WNNM). Consequently, many small singular values are shrunk to zero, which is unbeneficial for restoring image details. The other is that how to adaptively evaluate the importance of each singular value is still a suspending problem. In this paper, we propose a novel rank minimization method, namely adaptive hybrid norm minimization (AHNM) model, to solve the above problems. Specifically, for each singular value, we employ l2-norm to compensate for l1-norm, and introduce a significance factor to assess its importance adaptively. More importantly, we show that closed-form solutions for all subproblems can be derived simply by using alternating optimization. With the aid of the proposed AHNM model, we further develop a general yet effective image restoration algorithm based on the nonlocal self-similarity (NSS) of images. Numerous experimental results demonstrate that the proposed AHNM model consistently outperforms many state-of-the-art restoration methods, including model-based methods and deep learning-based methods.

Large-Scale Hyperspectral Image Restoration via a Superpixel Distributed Algorithm Based on Graph Signal Processing

Hyperspectral image (HSI) is often disturbed by various kinds of noise, which brings great challenges to subsequent applications. Many of the existing restoration algorithms do not scale well for HSI with large size. This paper proposes a novel mixed-noise removal method for HSI with large size, by leveraging the superpixel segmentation-based technology and distributed algorithm based on graph signal processing. First, the underlying structure of the HSI is modeled by a two-layer architecture graph. The upper layer, called skeleton graph, is a rough graph constructed by using the modified <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i> -nearest-neighborhood algorithm and its nodes correspond to a series of superpixels formed by HSI segmentation. The skeleton graph can efficiently characterize the inter-correlations between superpixels, while preserving the boundary information and reducing the computational complexity. The lower layer, called detailed graph consisting of a series of local graphs which are constructed to model the similarities between pixels. Second, based on the two-layer graph architecture, the HSI restoration problem is formulated as a series of optimization problems each of which resides on a subgraph. In each optimization problem, a graph Laplacian regularization is defined and incorporated into a low-rank-based model. Third, a novel distributed algorithm is tailored for the restoration problem, by using the information interaction between the nodes of skeleton graph and subgraphs. Numerical experiments conducted on both synthetic and real-world datasets demonstrate the effectiveness of the proposed restoration algorithm compared with existing methods.

A Tabu-search-based Algorithm for Distribution Network Restoration to Improve Reliability and Resiliency

Fault restoration techniques have always been crucial for distribution system operators (DSOs). In the last decade, it started to gain more and more importance due to the introduction of output-based regulations where DSO performances are evaluated according to frequency and duration of energy supply interruptions. The paper presents a tabu-search-based algorithm able to assist distribution network operational engineers in identifying solutions to restore the energy supply after permanent faults. According to the network property, two objective functions are considered to optimize either reliability or resiliency. The mathematical formulation includes the traditional feeders, number of switching operation limit, and radiality constraints. Thanks to the DSO of Milan, Unareti, the proposed algorithm has been tested on a real distribution network to investigate its effectiveness.

Surgical treatment of combined injuries of the neck and shoulder joints

To develop the algorithm for effective surgical restoration of shoulder joint and neck functions and acceleration of social and labor rehabilitation. There were 116 patients with combined consequences of burns of the neck and shoulder joints between 2012 and 2021. These ones amounted to 29.4% of all patients with lesions of the neck or shoulder joints. Simultaneous surgeries with correction of post-burn cicatricial deformities and contractures were performed in 66 patients (56.9%). Age of patients ranged from 18 to 72 years, and 96% of them were employable. There were 89 (76.7%) women and 27 (23.3%) men. We assessed spread and localization of cicatricial process, as well as restriction of mobility of the neck and shoulder joint to select optimal surgical approach. Classification of neck deformities and contractures of shoulder joints considering severity of cicatricial lesion and functional impairment made it possible to systematize the approach to reconstructive procedures. Reconstructive surgery included repair with local tissues including skin-fatty flap, non-perforated split or full-thickness skin autograft, rotated flaps including those based on perforator vessels, as well as preliminary skin stretching. In general, 116 patients with combined lesions of the neck and shoulder joints underwent 314 surgeries. To accelerate rehabilitation, we performed simultaneous surgeries with correction of deformities and contractures in 66 patients (56.9%). Staged reconstructive surgeries were carried out in 50 patients. Acute dermotension and skin-fatty neck flap grafting were the most common for deformities and contractures of the neck. Skin-fatty axillary flap was used in most patients with contractures of shoulder joints. Simultaneous surgeries can accelerate rehabilitation. Correct algorithm of staged surgical treatment reduces rehabilitation period and eliminates functional disorders.

Service Restoration of AC–DC Distribution Grids Based on Multiple-Criteria Decision Analysis

Modern distribution grids are transforming due to the increasing amount of load and generation based on DC technologies, whose interconnection is facilitated by the upcoming AC-DC distribution networks. Their fault management is challenged by new issues related to the power transferred among AC and DC sub-networks. In light of this, the present paper proposes a novel Service Restoration (SR) algorithm, specifically tailored for AC-DC distribution grids, that optimizes the re-energization by establishing priorities of disconnected bus groups and computing, as candidate solutions, hierarchical combinations of normally open and normally closed switches. To overcome the limitations of existing approaches, a Multiple Criteria Decision Analysis (MCDA) is proposed to combine and objectively prioritize different SR goals (i.e., the use of telecontrolled switches, the minimization of power losses, and the applicability of the proposed solutions in a defined time horizon), and ultimately make the grid operator benefit from the possibility to flexibly tune different operational objectives. The proposed algorithm allows to effectively discriminating competing solutions, i.e. whence and how to re-energize disconnected buses, and complies with the time requirements for field implementation. The results prove the crucial role of DC sub-networks, associated to the control of power injection from AC-DC converters, in enhancing the SR by improving its targets and increasing the number of re-energized loads. Ultimately, the effect of MCDA comparison parameters on the SR outcomes is quantitatively investigated via global sensitivity analysis, whose adoption is recommended for supporting the grid operator in the algorithm implementation.

Two-Stage Underwater Image Restoration Algorithm Based on Physical Model and Causal Intervention

Underwater images often suffer from severe color degradation, haze and local blur, which are caused by the scattering and absorption effects of light in water. Firstly, to address the lack of annotations in underwater images, we propose a multi-degradation rate underwater image degradation model. Additionally, we use the generative adversarial network (GAN) to guide the underwater image degradation model and generate paired images that can be used for underwater image restoration (UIR) network training. Also, given the problems of poor restoration quality, serious loss of detail, and slow inference speed of existing deep learning algorithms, we construct an underwater image restoration network that can reference in real-time. Moreover, through causal interventions in the image generation process, spurious correlations between global features and detailed features are eliminated. As a result, the detail generation ability of the image is improved. Experiments on real underwater image datasets demonstrate that compared with existing methods, our proposed method more effectively solves the problem of underwater image degradation.

An adaptive image restoration algorithm based on hybrid total variation regularization

In imaging systems, the mixed Poisson-Gaussian noise (MPGN) model can accurately describe the noise present. Total variation (TV) regularization-based methods have been widely utilized for Poisson-Gaussian removal with edge-preserving. However, TV regularization sometimes causes staircase artifacts with piecewise constants. To overcome this issue, we propose a new model in which the regularization term is represented by a combination of total variation and high-order total variation. We study the existence and uniqueness of the minimizer for the considered model. Numerically, the minimization problem can be efficiently solved by the alternating minimization method. Furthermore, we give rigorous convergence analyses of our algorithm. Experiments results are provided to demonstrate the superiority of our proposed hybrid model and algorithm for deblurring and denoising images simultaneously, in comparison with several state-of-the-art numerical algorithms.

Retracted: Ultrasonic Image Restoration Algorithm for Prevention of Nervous Disorders during the Recovery Period of Patients Receiving Sevoflurane Anesthesia.

[This retracts the article DOI: 10.1155/2021/6124346.].

A Comprehensive Review of Deep Learning-Based Real-World Image Restoration

Real-world imagery does not always exhibit good visibility and clean content, but often suffers from various kinds of degradations (e.g., noise, blur, rain drops, fog, color distortion, etc.), which severely affect vision-driven tasks (e.g., image classification, target recognition, and tracking, etc.). Thus, restoring the true scene from such degraded images is of significance. In recent years, a large body of deep learning-based image processing works has been exploited due to the advances in deep neural networks. This paper aims to make a comprehensive review of real-world image restoration algorithms and beyond. More specifically, this review provides overviews of critical benchmark datasets, image quality assessment methods, and four major categories of deep learning-based image restoration methods, i.e., based on convolutional neural network (CNN), generative adversarial network (GAN), Transformer, and multi-layer perceptron (MLP). The paper highlights the latest developments and advances in each category of network architecture to provide an up-to-date overview. Moreover, the representative state-of-the-art image restoration methods are compared visually and numerically. Finally, for real-world image restoration, the current situations are objectively assessed, challenges are discussed, and future directions and trends are presented.

Restoration Algorithm for Honeycomb Artifacts Based on Optical Fiber Imaging

Restoration Algorithm for Honeycomb Artifacts Based on Optical Fiber Imaging

Semi-automatic fingerprint image restoration algorithm using a partial differential equation

&lt;abstract&gt;&lt;p&gt;A fingerprint is the unique, complex pattern of ridges and valleys on the surface of an individual's fingertip. Fingerprinting is one of the most popular and widely used biometric authentication methods for personal identification because of its reliability, acceptability, high level of security, and low cost. When using fingerprints as a biometric, restoring poor-quality or damaged fingerprints is an essential process for accurate verification. In this study, we present a semi-automatic fingerprint image restoration method using a partial differential equation to repair damaged fingerprint images. The proposed algorithm is based on the Cahn-Hilliard (CH) equation with a source term, which was developed for simulating pattern formation during the phase separation of diblock copolymers in chemical engineering applications. In previous work, in order to find an optimal model and numerical parameter values in the governing equation, we had to make several trial and error preliminary attempts. To overcome these problems, the proposed novel algorithm minimizes user input and automatically computes the necessary model and numerical parameter values of the governing equation. Computational simulations on various damaged fingerprint samples are presented to demonstrate the superior performance of the proposed method.&lt;/p&gt;&lt;/abstract&gt;

선박에서 증강현실 위치 정합 활용을 위한 기계학습 기반의 마커 복원 방법 연구

The interior of the ship is very complex and the equipment is equipped with pipes, valves, supports, etc. In order to utilize augmented reality in such an environment, it is more appropriate to use markers rather than markerless, which creates a model based on the characteristics of the target equipment. However, it is difficult to apply the marker because a lot of corrosion or damage to the marker may occur in the ship. Therefore, in this study, when a marker is damaged, it is intended to restore the marker using GAN among machine learning techniques. At this time, the model was built using the Pix2Pix, Cycle GAN, and Disco GAN algorithms widely used for images among GAN algorithms. Finally, an efficient marker restoration algorithm was verified by qualitatively and quantitatively comparing the model results.

The application of directional derivative in the design of animation characters and background elements

Abstract In the process of designing animation characters and background elements, there may be a high degree of visual blur, resulting in a strong sense of picture distortion, and it is easy to expose the incomplete picture. Accordingly, this paper proposes to use directional derivatives to deal with animation-like visual problems. This method is based on the theoretical basis of directional derivatives, combined with the current mathematical methods of animation character and background element design, and defines the important role of directional derivatives in animation and background design, and more effectively enhances the visual results of animation characters. In the research of clarity and distortion, this paper uses directional derivative derivation as the cutting-in method to test the algorithm for visual simulation and restoration of animated characters and background elements so that the algorithm can be used for each animation character and background element. The defect point is calculated, and the clarity and self-healing ability of the video itself are improved by the influence of the mathematical parameters of the surrounding known points on itself and the key variable of the directional derivative in the field. The results show that the directional derivative can play a role in promoting sublimation in the design of animated characters and background elements.

Semisupervised Surveillance Video Character Extraction and Recognition With Attentional Learning Multiframe Fusion

Character extraction in the video is very helpful to the understanding of the video content, especially the artificially superimposed characters such as time and place in the surveillance video. However, the performance of the existing algorithms does not meet the needs of application. Therefore, the authors improve semisupervised surveillance video character extraction and recognition with attentional learning multiframe feature fusion. First, the multiframe fusion strategy based on an attention mechanism is adopted to solve the target missing problem, and the Dense ASPP network is introduced to solve the character multiscale problem. Second, a character image denoising algorithm based on semisupervised fuzzy C-means clustering is proposed to isolate and extract clean binary character images. Finally, for some video characters that may involve privacy, traditional and deep learning-based video restoration algorithms are used for characteristic elimination.