No Cover Image

Journal article 197 views 67 downloads

Image restoration with group sparse representation and low‐rank group residual learning

Zhaoyuan Cai, Xianghua Xie Orcid Logo, Jingjing Deng, Zengfa Dou Orcid Logo, Bo Tong, Xiaoke Ma Orcid Logo

IET Image Processing

Swansea University Author: Xianghua Xie Orcid Logo

  • 64966.pdf

    PDF | Version of Record

    This is an open access article under the terms of theCreative Commons Attribution-NonCommercial-NoDerivsLicense, which permits use and distribution in any medium, provided theoriginal work is properly cited, the use is non-commercial and no modifications or adaptations are made

    Download (10.48MB)

Check full text

DOI (Published version): 10.1049/ipr2.12982

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 practic...

Full description

Published in: IET Image Processing
ISSN: 1751-9659 1751-9667
Published: Institution of Engineering and Technology (IET)
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa64966
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2023-11-12T21:48:44Z
last_indexed 2023-11-12T21:48:44Z
id cronfa64966
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>64966</id><entry>2023-11-12</entry><title>Image restoration with group sparse representation and low‐rank group residual learning</title><swanseaauthors><author><sid>b334d40963c7a2f435f06d2c26c74e11</sid><ORCID>0000-0002-2701-8660</ORCID><firstname>Xianghua</firstname><surname>Xie</surname><name>Xianghua Xie</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2023-11-12</date><deptcode>SCS</deptcode><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><type>Journal Article</type><journal>IET Image Processing</journal><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher>Institution of Engineering and Technology (IET)</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1751-9659</issnPrint><issnElectronic>1751-9667</issnElectronic><keywords/><publishedDay>0</publishedDay><publishedMonth>0</publishedMonth><publishedYear>0</publishedYear><publishedDate>0001-01-01</publishedDate><doi>10.1049/ipr2.12982</doi><url>http://dx.doi.org/10.1049/ipr2.12982</url><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm>Other</apcterm><funders/><projectreference/><lastEdited>2023-11-21T10:54:31.4245298</lastEdited><Created>2023-11-12T21:42:50.3256973</Created><path><level id="1">College of Science</level><level id="2">Computer Science</level></path><authors><author><firstname>Zhaoyuan</firstname><surname>Cai</surname><order>1</order></author><author><firstname>Xianghua</firstname><surname>Xie</surname><orcid>0000-0002-2701-8660</orcid><order>2</order></author><author><firstname>Jingjing</firstname><surname>Deng</surname><order>3</order></author><author><firstname>Zengfa</firstname><surname>Dou</surname><orcid>0000-0002-5162-6244</orcid><order>4</order></author><author><firstname>Bo</firstname><surname>Tong</surname><order>5</order></author><author><firstname>Xiaoke</firstname><surname>Ma</surname><orcid>0000-0002-5604-7137</orcid><order>6</order></author></authors><documents><document><filename>64966__29068__a0508ceeda294222a8e379b96f6b2743.pdf</filename><originalFilename>64966.pdf</originalFilename><uploaded>2023-11-21T10:53:33.7028194</uploaded><type>Output</type><contentLength>10984068</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>This is an open access article under the terms of theCreative Commons Attribution-NonCommercial-NoDerivsLicense, which permits use and distribution in any medium, provided theoriginal work is properly cited, the use is non-commercial and no modifications or adaptations are made</documentNotes><copyrightCorrect>false</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling v2 64966 2023-11-12 Image restoration with group sparse representation and low‐rank group residual learning b334d40963c7a2f435f06d2c26c74e11 0000-0002-2701-8660 Xianghua Xie Xianghua Xie true false 2023-11-12 SCS 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. Journal Article IET Image Processing Institution of Engineering and Technology (IET) 1751-9659 1751-9667 0 0 0 0001-01-01 10.1049/ipr2.12982 http://dx.doi.org/10.1049/ipr2.12982 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University Other 2023-11-21T10:54:31.4245298 2023-11-12T21:42:50.3256973 College of Science Computer Science Zhaoyuan Cai 1 Xianghua Xie 0000-0002-2701-8660 2 Jingjing Deng 3 Zengfa Dou 0000-0002-5162-6244 4 Bo Tong 5 Xiaoke Ma 0000-0002-5604-7137 6 64966__29068__a0508ceeda294222a8e379b96f6b2743.pdf 64966.pdf 2023-11-21T10:53:33.7028194 Output 10984068 application/pdf Version of Record true This is an open access article under the terms of theCreative Commons Attribution-NonCommercial-NoDerivsLicense, which permits use and distribution in any medium, provided theoriginal work is properly cited, the use is non-commercial and no modifications or adaptations are made false eng http://creativecommons.org/licenses/by/4.0/
title Image restoration with group sparse representation and low‐rank group residual learning
spellingShingle Image restoration with group sparse representation and low‐rank group residual learning
Xianghua Xie
title_short Image restoration with group sparse representation and low‐rank group residual learning
title_full Image restoration with group sparse representation and low‐rank group residual learning
title_fullStr Image restoration with group sparse representation and low‐rank group residual learning
title_full_unstemmed Image restoration with group sparse representation and low‐rank group residual learning
title_sort Image restoration with group sparse representation and low‐rank group residual learning
author_id_str_mv b334d40963c7a2f435f06d2c26c74e11
author_id_fullname_str_mv b334d40963c7a2f435f06d2c26c74e11_***_Xianghua Xie
author Xianghua Xie
author2 Zhaoyuan Cai
Xianghua Xie
Jingjing Deng
Zengfa Dou
Bo Tong
Xiaoke Ma
format Journal article
container_title IET Image Processing
institution Swansea University
issn 1751-9659
1751-9667
doi_str_mv 10.1049/ipr2.12982
publisher Institution of Engineering and Technology (IET)
college_str College of Science
hierarchytype
hierarchy_top_id collegeofscience
hierarchy_top_title College of Science
hierarchy_parent_id collegeofscience
hierarchy_parent_title College of Science
department_str Computer Science{{{_:::_}}}College of Science{{{_:::_}}}Computer Science
url http://dx.doi.org/10.1049/ipr2.12982
document_store_str 1
active_str 0
description 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.
published_date 0001-01-01T10:54:32Z
_version_ 1783170672685481984
score 11.016235

Similar Items