Truncated loss-based Res2Net for non-Gaussian noise removal

Many current image denoising works focus on Gaussian noise removal. However, in many real-life applications, the noise in an image can follow non-Gaussian distributions, such as compressed speckle noise, salt-and-pepper impulse noise (SPIN), and random-valued impulse noise (RVIN). In such scenarios,...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Signal, image and video processing image and video processing, 2024-09, Vol.18 (10), p.6601-6611
Hauptverfasser: Cheng, Li, Guo, Zhichang, Li, Yao, Xing, Yuming
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 6611
container_issue 10
container_start_page 6601
container_title Signal, image and video processing
container_volume 18
creator Cheng, Li
Guo, Zhichang
Li, Yao
Xing, Yuming
description Many current image denoising works focus on Gaussian noise removal. However, in many real-life applications, the noise in an image can follow non-Gaussian distributions, such as compressed speckle noise, salt-and-pepper impulse noise (SPIN), and random-valued impulse noise (RVIN). In such scenarios, image denoising models with mean squared error loss will fail to obtain the best noise estimation results. Thus, we propose a non-Gaussian denoising convolutional neural network (DTNet) with truncation loss, which can address compressed speckle noise, SPIN, and RVIN with the same denoising framework. The model is composed of Res2Net blocks with the ability to extract multiscale information. Experiments show that our proposed DTNet method can effectively remove compressed speckle noise and impulse noise, including SPIN and RVIN. In particular, DTNet can recover the original images from images with 90% SPIN or images with 70% RVIN.
doi_str_mv 10.1007/s11760-024-03338-3
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_3091273582</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3091273582</sourcerecordid><originalsourceid>FETCH-LOGICAL-c200t-9a3ca8136a3ad94f7e8a24288ab32c158fe1f0fc346d6b23acee724d0b0c41b23</originalsourceid><addsrcrecordid>eNp9UMFKAzEQDaJgqf0BTwueozOZ7W6KJynaCkVB6jnMZhNpaXdrsiv496au6M25zJvhvTfME-IS4RoBypuIWBYgQeUSiEhLOhEj1AVJLBFPfzHQuZjEuIVUpEpd6JG4XYe-sdy5Otu1McqKY4IvLqon12W-DVnTNnLBfYwbbtKwiS4Lbt9-8O5CnHneRTf56WPx-nC_ni_l6nnxOL9bSasAOjljsqyRCiauZ7kvnWaVK625ImVxqr1DD95SXtRFpYitc6XKa6jA5pgWY3E1-B5C-9672Jlt24cmnTQEM1QlTfWRpQaWDemR4Lw5hM2ew6dBMMeczJCTSTmZ75wMJRENopjIzZsLf9b_qL4AC5Jpuw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3091273582</pqid></control><display><type>article</type><title>Truncated loss-based Res2Net for non-Gaussian noise removal</title><source>Springer Nature - Complete Springer Journals</source><creator>Cheng, Li ; Guo, Zhichang ; Li, Yao ; Xing, Yuming</creator><creatorcontrib>Cheng, Li ; Guo, Zhichang ; Li, Yao ; Xing, Yuming</creatorcontrib><description>Many current image denoising works focus on Gaussian noise removal. However, in many real-life applications, the noise in an image can follow non-Gaussian distributions, such as compressed speckle noise, salt-and-pepper impulse noise (SPIN), and random-valued impulse noise (RVIN). In such scenarios, image denoising models with mean squared error loss will fail to obtain the best noise estimation results. Thus, we propose a non-Gaussian denoising convolutional neural network (DTNet) with truncation loss, which can address compressed speckle noise, SPIN, and RVIN with the same denoising framework. The model is composed of Res2Net blocks with the ability to extract multiscale information. Experiments show that our proposed DTNet method can effectively remove compressed speckle noise and impulse noise, including SPIN and RVIN. In particular, DTNet can recover the original images from images with 90% SPIN or images with 70% RVIN.</description><identifier>ISSN: 1863-1703</identifier><identifier>EISSN: 1863-1711</identifier><identifier>DOI: 10.1007/s11760-024-03338-3</identifier><language>eng</language><publisher>London: Springer London</publisher><subject>Artificial neural networks ; Computer Imaging ; Computer Science ; Image Processing and Computer Vision ; Multimedia Information Systems ; Noise reduction ; Original Paper ; Pattern Recognition and Graphics ; Random noise ; Signal,Image and Speech Processing ; Vision</subject><ispartof>Signal, image and video processing, 2024-09, Vol.18 (10), p.6601-6611</ispartof><rights>The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c200t-9a3ca8136a3ad94f7e8a24288ab32c158fe1f0fc346d6b23acee724d0b0c41b23</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11760-024-03338-3$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11760-024-03338-3$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,777,781,27905,27906,41469,42538,51300</link.rule.ids></links><search><creatorcontrib>Cheng, Li</creatorcontrib><creatorcontrib>Guo, Zhichang</creatorcontrib><creatorcontrib>Li, Yao</creatorcontrib><creatorcontrib>Xing, Yuming</creatorcontrib><title>Truncated loss-based Res2Net for non-Gaussian noise removal</title><title>Signal, image and video processing</title><addtitle>SIViP</addtitle><description>Many current image denoising works focus on Gaussian noise removal. However, in many real-life applications, the noise in an image can follow non-Gaussian distributions, such as compressed speckle noise, salt-and-pepper impulse noise (SPIN), and random-valued impulse noise (RVIN). In such scenarios, image denoising models with mean squared error loss will fail to obtain the best noise estimation results. Thus, we propose a non-Gaussian denoising convolutional neural network (DTNet) with truncation loss, which can address compressed speckle noise, SPIN, and RVIN with the same denoising framework. The model is composed of Res2Net blocks with the ability to extract multiscale information. Experiments show that our proposed DTNet method can effectively remove compressed speckle noise and impulse noise, including SPIN and RVIN. In particular, DTNet can recover the original images from images with 90% SPIN or images with 70% RVIN.</description><subject>Artificial neural networks</subject><subject>Computer Imaging</subject><subject>Computer Science</subject><subject>Image Processing and Computer Vision</subject><subject>Multimedia Information Systems</subject><subject>Noise reduction</subject><subject>Original Paper</subject><subject>Pattern Recognition and Graphics</subject><subject>Random noise</subject><subject>Signal,Image and Speech Processing</subject><subject>Vision</subject><issn>1863-1703</issn><issn>1863-1711</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9UMFKAzEQDaJgqf0BTwueozOZ7W6KJynaCkVB6jnMZhNpaXdrsiv496au6M25zJvhvTfME-IS4RoBypuIWBYgQeUSiEhLOhEj1AVJLBFPfzHQuZjEuIVUpEpd6JG4XYe-sdy5Otu1McqKY4IvLqon12W-DVnTNnLBfYwbbtKwiS4Lbt9-8O5CnHneRTf56WPx-nC_ni_l6nnxOL9bSasAOjljsqyRCiauZ7kvnWaVK625ImVxqr1DD95SXtRFpYitc6XKa6jA5pgWY3E1-B5C-9672Jlt24cmnTQEM1QlTfWRpQaWDemR4Lw5hM2ew6dBMMeczJCTSTmZ75wMJRENopjIzZsLf9b_qL4AC5Jpuw</recordid><startdate>20240901</startdate><enddate>20240901</enddate><creator>Cheng, Li</creator><creator>Guo, Zhichang</creator><creator>Li, Yao</creator><creator>Xing, Yuming</creator><general>Springer London</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20240901</creationdate><title>Truncated loss-based Res2Net for non-Gaussian noise removal</title><author>Cheng, Li ; Guo, Zhichang ; Li, Yao ; Xing, Yuming</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c200t-9a3ca8136a3ad94f7e8a24288ab32c158fe1f0fc346d6b23acee724d0b0c41b23</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Artificial neural networks</topic><topic>Computer Imaging</topic><topic>Computer Science</topic><topic>Image Processing and Computer Vision</topic><topic>Multimedia Information Systems</topic><topic>Noise reduction</topic><topic>Original Paper</topic><topic>Pattern Recognition and Graphics</topic><topic>Random noise</topic><topic>Signal,Image and Speech Processing</topic><topic>Vision</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Cheng, Li</creatorcontrib><creatorcontrib>Guo, Zhichang</creatorcontrib><creatorcontrib>Li, Yao</creatorcontrib><creatorcontrib>Xing, Yuming</creatorcontrib><collection>CrossRef</collection><jtitle>Signal, image and video processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Cheng, Li</au><au>Guo, Zhichang</au><au>Li, Yao</au><au>Xing, Yuming</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Truncated loss-based Res2Net for non-Gaussian noise removal</atitle><jtitle>Signal, image and video processing</jtitle><stitle>SIViP</stitle><date>2024-09-01</date><risdate>2024</risdate><volume>18</volume><issue>10</issue><spage>6601</spage><epage>6611</epage><pages>6601-6611</pages><issn>1863-1703</issn><eissn>1863-1711</eissn><abstract>Many current image denoising works focus on Gaussian noise removal. However, in many real-life applications, the noise in an image can follow non-Gaussian distributions, such as compressed speckle noise, salt-and-pepper impulse noise (SPIN), and random-valued impulse noise (RVIN). In such scenarios, image denoising models with mean squared error loss will fail to obtain the best noise estimation results. Thus, we propose a non-Gaussian denoising convolutional neural network (DTNet) with truncation loss, which can address compressed speckle noise, SPIN, and RVIN with the same denoising framework. The model is composed of Res2Net blocks with the ability to extract multiscale information. Experiments show that our proposed DTNet method can effectively remove compressed speckle noise and impulse noise, including SPIN and RVIN. In particular, DTNet can recover the original images from images with 90% SPIN or images with 70% RVIN.</abstract><cop>London</cop><pub>Springer London</pub><doi>10.1007/s11760-024-03338-3</doi><tpages>11</tpages></addata></record>
fulltext fulltext
identifier ISSN: 1863-1703
ispartof Signal, image and video processing, 2024-09, Vol.18 (10), p.6601-6611
issn 1863-1703
1863-1711
language eng
recordid cdi_proquest_journals_3091273582
source Springer Nature - Complete Springer Journals
subjects Artificial neural networks
Computer Imaging
Computer Science
Image Processing and Computer Vision
Multimedia Information Systems
Noise reduction
Original Paper
Pattern Recognition and Graphics
Random noise
Signal,Image and Speech Processing
Vision
title Truncated loss-based Res2Net for non-Gaussian noise removal
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T06%3A03%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Truncated%20loss-based%20Res2Net%20for%20non-Gaussian%20noise%20removal&rft.jtitle=Signal,%20image%20and%20video%20processing&rft.au=Cheng,%20Li&rft.date=2024-09-01&rft.volume=18&rft.issue=10&rft.spage=6601&rft.epage=6611&rft.pages=6601-6611&rft.issn=1863-1703&rft.eissn=1863-1711&rft_id=info:doi/10.1007/s11760-024-03338-3&rft_dat=%3Cproquest_cross%3E3091273582%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3091273582&rft_id=info:pmid/&rfr_iscdi=true