The Image Restoration Method Based on Patch Sparsity Propagation in Big Data Environment

2018 ◽  
Vol 22 (7) ◽  
pp. 1072-1076
Author(s):  
Kun Ling Wang ◽  
Keyword(s):  
Big Data ◽  
Image Restoration ◽  
Sparse Coding ◽  
Design Method ◽  
Image Data ◽  
Propagation Analysis ◽  
Blurred Image ◽  
Data Environment ◽  
Restoration Method ◽  
Characteristics Of Image

The traditional image restoration method only uses the original image data as a dictionary to make sparse representation of the pending blocks, which leads to the poor adaptation of the dictionary and the blurred image of the restoration. And only the effective information around the restored block is used for sparse coding, without considering the characteristics of image blocks, and the prior knowledge is limited. Therefore, in the big data environment, a new method of image restoration based on structural coefficient propagation is proposed. The clustering method is used to divide the image into several small area image blocks with similar structures, classify the images according to the features, and train the different feature types of the image blocks and their corresponding adaptive dictionaries. According to the characteristics of the restored image blocks, the restoration order is determined through the sparse structural propagation analysis, and the image restoration is achieved by sparse coding. The design method is programmed, and the image restoration in big data environment is realized by designing the system. Experimental results show that the proposed method can effectively restore images and has high quality and efficiency.

Image Restoration via Group l2,1 Norm-Based Structural Sparse Representation

2017 ◽  
Vol 32 (04) ◽  
pp. 1854008 ◽  
Author(s):  
Kai Song Zhang ◽  
Luo Zhong ◽  
Xuan Ya Zhang
Keyword(s):  
Image Restoration ◽  
Sparse Representation ◽  
Sparse Coding ◽  
Structural Information ◽  
Signal To Noise Ratio ◽  
Coefficient Matrix ◽  
Optimization Approach ◽  
Signal To Noise ◽  
Nonlinear Features ◽  
Characteristics Of Image

Sparse representation has recently been extensively studied in the field of image restoration. Many sparsity-based approaches enforce sparse coding on patches with certain constraints. However, extracting structural information is a challenging task in the field image restoration. Motivated by the fact that structured sparse representation (SSR) method can capture the inner characteristics of image structures, which helps in finding sparse representations of nonlinear features or patterns, we propose the SSR approach for image restoration. Specifically, a generalized model is developed using structured restraint, namely, the group [Formula: see text]-norm of the coefficient matrix is introduced in the traditional sparse representation with respect to minimizing the differences within classes and maximizing the differences between classes for sparse representation, and its applications with image restoration are also explored. The sparse coefficients of SSR are obtained through iterative optimization approach. Experimental results have shown that the proposed SSR technique can significantly deliver the reconstructed images with high quality, which manifest the effectiveness of our approach in both peak signal-to-noise ratio performance and visual perception.

scholarly journals Data-driven image restoration with option-driven learning for big and small astronomical image data sets

2020 ◽  
Vol 501 (1) ◽  
pp. 291-301
Author(s):  
Peng Jia ◽  
Runyu Ning ◽  
Ruiqi Sun ◽  
Xiaoshan Yang ◽  
Dongmei Cai
Keyword(s):  
Image Restoration ◽  
Learning Strategies ◽  
Simulated Data ◽  
Image Data ◽  
Data Driven ◽  
Generative Adversarial Networks ◽  
Supervised Learning Algorithms ◽  
Reference Images ◽  
Astronomical Images ◽  
Restoration Method

ABSTRACT Image restoration methods are commonly used to improve the quality of astronomical images. In recent years, developments of deep neural networks and increments of the number of astronomical images have evoked a lot of data-driven image restoration methods. However, most of these methods belong to supervised learning algorithms, which require paired images either from real observations or simulated data as training set. For some applications, it is hard to get enough paired images from real observations and simulated images are quite different from real observed ones. In this paper, we propose a new data-driven image restoration method based on generative adversarial networks with option-driven learning. Our method uses several high-resolution images as references and applies different learning strategies when the number of reference images is different. For sky surveys with variable observation conditions, our method can obtain very stable image restoration results, regardless of the number of reference images.

Effect of SNR Estimation in Defocus Blurred Image Restoration

2012 ◽  
Vol 239-240 ◽  
pp. 1113-1117
Author(s):  
Feng Qing Qin
Keyword(s):  
Image Restoration ◽  
Signal To Noise Ratio ◽  
Parameter Analysis ◽  
Snr Estimation ◽  
Blind Image Restoration ◽  
Blurred Image ◽  
Local Deviation ◽  
Restoration Method ◽  
Ringing Effect ◽  
Blind Image

A blind image restoration method is proposed to improve the quality of the image blurred by camera defocus and system noise. Firstly, the focus point spread function (PSF) of the blurred image is estimated through error-parameter analysis method. Secondly, the Signal-to-Noise Ratio (SNR) of the blurred image is estimated through local deviation method. Thirdly, utilizing the estimated defocus PSF and SNR, image restoration is performed through Wiener filtering method, in which circulation boundary method is adopted to reduce ringing effect. Experimental results show that the SNR of the blurred image is estimated approximately, and verify the great effect of SNR estimation in blind image restoration.

A Motion Blurred Image Restoration Method Based on Wiener Filtering

2011 ◽  
Vol 403-408 ◽  
pp. 1664-1667 ◽  
Author(s):  
Qian Qian Quan
Keyword(s):  
Image Restoration ◽  
Motion Blur ◽  
Experimental Results ◽  
Wiener Filtering ◽  
Degradation Model ◽  
Image Blurring ◽  
Blurred Image ◽  
Working Principle ◽  
Restoration Method ◽  
Blurred Images

To the deficiencies of traditional methods for avoiding motion image blurring, a motion blur image restoration method is studied based on Wiener filtering in this paper. The formation factors of motion-blurred images and the imaging process are analyzed, and the motion blur degradation model is established. It introduced the working principle of Wiener filtering, described the steps of blurred image restoration in details. The experiment testing and data analyzing are also conducted. Experimental results showed that the method can has good performance.

Aerial Transmission Lines Image Restoration Technology Research Based on the Improved Maximum Entropy

2013 ◽  
Vol 401-403 ◽  
pp. 1315-1318
Author(s):  
Bao Shu Li ◽  
Wen Li Wei ◽  
Ke Bin Cui ◽  
Xue Tao Xu
Keyword(s):  
Image Restoration ◽  
Maximum Entropy ◽  
Transmission Lines ◽  
Maximum Entropy Method ◽  
Entropy Method ◽  
First Order ◽  
Image Blurring ◽  
Blurred Image ◽  
Restoration Method

According to the limitations of the shooting environment, captured image exist the phenomenon of image blurring and noise. This paper proposes that the improved maximum entropy method recovery blurred image which acquire in aerial. Finally, according to the first order Markoff theory to evaluate the quality of the processed image, the results show that maximum entropy image restoration method compared to the conventional approach increase image clarity and details more better.

Big Data Environment and Humanities Platform

2017 ◽  
Vol 39 (5) ◽  
pp. 177-202
Author(s):  
Hyun-Cheol Choi
Keyword(s):  
Big Data ◽  
Data Environment
Sign in / Sign up

Export Citation Format

Share Document