Deep Learning-Based Picture-Wise Just Noticeable Distortion Prediction Model for Image Compression

Picture Wise Just Noticeable Difference (PW-JND), which accounts for the minimum difference of a picture that human visual system can perceive, can be widely used in perception-oriented image and video processing. However, the conventional Just Noticeable Difference (JND) models calculate the JND th...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing 2020-01, Vol.29, p.641-656
Hauptverfasser: Liu, Huanhua, Zhang, Yun, Zhang, Huan, Fan, Chunling, Kwong, Sam, Kuo, C.-C. Jay, Fan, Xiaoping
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 656
container_issue
container_start_page 641
container_title IEEE transactions on image processing
container_volume 29
creator Liu, Huanhua
Zhang, Yun
Zhang, Huan
Fan, Chunling
Kwong, Sam
Kuo, C.-C. Jay
Fan, Xiaoping
description Picture Wise Just Noticeable Difference (PW-JND), which accounts for the minimum difference of a picture that human visual system can perceive, can be widely used in perception-oriented image and video processing. However, the conventional Just Noticeable Difference (JND) models calculate the JND threshold for each pixel or sub-band separately, which may not reflect the total masking effect of a picture accurately. In this paper, we propose a deep learning based PW-JND prediction model for image compression. Firstly, we formulate the task of predicting PW-JND as a multi-class classification problem, and propose a framework to transform the multi-class classification problem to a binary classification problem solved by just one binary classifier. Secondly, we construct a deep learning based binary classifier named perceptually lossy/lossless predictor which can predict whether an image is perceptually lossy to another or not. Finally, we propose a sliding window based search strategy to predict PW-JND based on the prediction results of the perceptually lossy/lossless predictor. Experimental results show that the mean accuracy of the perceptually lossy/lossless predictor reaches 92%, and the absolute prediction error of the proposed PW-JND model is 0.79 dB on average, which show the superiority of the proposed PW-JND model to the conventional JND models.
doi_str_mv 10.1109/TIP.2019.2933743
format Article
fullrecord <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_miscellaneous_2336981828</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8796396</ieee_id><sourcerecordid>2336981828</sourcerecordid><originalsourceid>FETCH-LOGICAL-c394t-57fe34bd4009244dd20cf2dbd7ab8b4a784a511b31be39044118a39710d542a53</originalsourceid><addsrcrecordid>eNpdkE1r3DAQhkVoyVd7DxSKoJdcvNVI8so6tpuPbtm2e0jJUUjWOCjY1layD_331bKbHAoDM_A-MwwPIVfAFgBMf35YbxecgV5wLYSS4oScg5ZQMSb5mzKzWlUKpD4jFzk_MwayhuUpORMgec2EOCfuBnFHN2jTGMan6qvN6Ok2tNOcsHoMGen3OU_0Z5xCi9b1SG9CnmKaQhzpNqEv6H78ET32tIuJrgf7hHQVh13CnEv2jrztbJ_x_bFfkt93tw-rb9Xm1_169WVTtULLqapVh0I6LxnTXErvOWs77p1X1jVOWtVIWwM4AQ6FZlICNFZoBczXkttaXJLrw91din9mzJMZQm6x7-2Icc6GC7HUDTS8Kein_9DnOKexfGc4141iimsoFDtQbYo5J-zMLoXBpr8GmNn7N8W_2fs3R_9l5ePx8OwG9K8LL8IL8OEABER8jRull6LUP7tliAA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2298707291</pqid></control><display><type>article</type><title>Deep Learning-Based Picture-Wise Just Noticeable Distortion Prediction Model for Image Compression</title><source>IEEE Electronic Library (IEL)</source><creator>Liu, Huanhua ; Zhang, Yun ; Zhang, Huan ; Fan, Chunling ; Kwong, Sam ; Kuo, C.-C. Jay ; Fan, Xiaoping</creator><creatorcontrib>Liu, Huanhua ; Zhang, Yun ; Zhang, Huan ; Fan, Chunling ; Kwong, Sam ; Kuo, C.-C. Jay ; Fan, Xiaoping</creatorcontrib><description>Picture Wise Just Noticeable Difference (PW-JND), which accounts for the minimum difference of a picture that human visual system can perceive, can be widely used in perception-oriented image and video processing. However, the conventional Just Noticeable Difference (JND) models calculate the JND threshold for each pixel or sub-band separately, which may not reflect the total masking effect of a picture accurately. In this paper, we propose a deep learning based PW-JND prediction model for image compression. Firstly, we formulate the task of predicting PW-JND as a multi-class classification problem, and propose a framework to transform the multi-class classification problem to a binary classification problem solved by just one binary classifier. Secondly, we construct a deep learning based binary classifier named perceptually lossy/lossless predictor which can predict whether an image is perceptually lossy to another or not. Finally, we propose a sliding window based search strategy to predict PW-JND based on the prediction results of the perceptually lossy/lossless predictor. Experimental results show that the mean accuracy of the perceptually lossy/lossless predictor reaches 92%, and the absolute prediction error of the proposed PW-JND model is 0.79 dB on average, which show the superiority of the proposed PW-JND model to the conventional JND models.</description><identifier>ISSN: 1057-7149</identifier><identifier>EISSN: 1941-0042</identifier><identifier>DOI: 10.1109/TIP.2019.2933743</identifier><identifier>PMID: 31425033</identifier><identifier>CODEN: IIPRE4</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Adaptation models ; Bit rate ; Classification ; Classifiers ; convolutional neural network ; Deep learning ; Distortion ; Image coding ; Image compression ; Image processing ; image quality assessment ; Just noticeable distortion ; Machine learning ; Masking ; Prediction models ; Predictive models ; Streaming media ; Video ; Visual perception ; Visualization</subject><ispartof>IEEE transactions on image processing, 2020-01, Vol.29, p.641-656</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c394t-57fe34bd4009244dd20cf2dbd7ab8b4a784a511b31be39044118a39710d542a53</citedby><cites>FETCH-LOGICAL-c394t-57fe34bd4009244dd20cf2dbd7ab8b4a784a511b31be39044118a39710d542a53</cites><orcidid>0000-0001-9474-5035 ; 0000-0002-5507-4985 ; 0000-0001-7484-7261 ; 0000-0003-0172-4070 ; 0000-0001-9457-7801</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8796396$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8796396$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/31425033$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Liu, Huanhua</creatorcontrib><creatorcontrib>Zhang, Yun</creatorcontrib><creatorcontrib>Zhang, Huan</creatorcontrib><creatorcontrib>Fan, Chunling</creatorcontrib><creatorcontrib>Kwong, Sam</creatorcontrib><creatorcontrib>Kuo, C.-C. Jay</creatorcontrib><creatorcontrib>Fan, Xiaoping</creatorcontrib><title>Deep Learning-Based Picture-Wise Just Noticeable Distortion Prediction Model for Image Compression</title><title>IEEE transactions on image processing</title><addtitle>TIP</addtitle><addtitle>IEEE Trans Image Process</addtitle><description>Picture Wise Just Noticeable Difference (PW-JND), which accounts for the minimum difference of a picture that human visual system can perceive, can be widely used in perception-oriented image and video processing. However, the conventional Just Noticeable Difference (JND) models calculate the JND threshold for each pixel or sub-band separately, which may not reflect the total masking effect of a picture accurately. In this paper, we propose a deep learning based PW-JND prediction model for image compression. Firstly, we formulate the task of predicting PW-JND as a multi-class classification problem, and propose a framework to transform the multi-class classification problem to a binary classification problem solved by just one binary classifier. Secondly, we construct a deep learning based binary classifier named perceptually lossy/lossless predictor which can predict whether an image is perceptually lossy to another or not. Finally, we propose a sliding window based search strategy to predict PW-JND based on the prediction results of the perceptually lossy/lossless predictor. Experimental results show that the mean accuracy of the perceptually lossy/lossless predictor reaches 92%, and the absolute prediction error of the proposed PW-JND model is 0.79 dB on average, which show the superiority of the proposed PW-JND model to the conventional JND models.</description><subject>Adaptation models</subject><subject>Bit rate</subject><subject>Classification</subject><subject>Classifiers</subject><subject>convolutional neural network</subject><subject>Deep learning</subject><subject>Distortion</subject><subject>Image coding</subject><subject>Image compression</subject><subject>Image processing</subject><subject>image quality assessment</subject><subject>Just noticeable distortion</subject><subject>Machine learning</subject><subject>Masking</subject><subject>Prediction models</subject><subject>Predictive models</subject><subject>Streaming media</subject><subject>Video</subject><subject>Visual perception</subject><subject>Visualization</subject><issn>1057-7149</issn><issn>1941-0042</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpdkE1r3DAQhkVoyVd7DxSKoJdcvNVI8so6tpuPbtm2e0jJUUjWOCjY1layD_331bKbHAoDM_A-MwwPIVfAFgBMf35YbxecgV5wLYSS4oScg5ZQMSb5mzKzWlUKpD4jFzk_MwayhuUpORMgec2EOCfuBnFHN2jTGMan6qvN6Ok2tNOcsHoMGen3OU_0Z5xCi9b1SG9CnmKaQhzpNqEv6H78ET32tIuJrgf7hHQVh13CnEv2jrztbJ_x_bFfkt93tw-rb9Xm1_169WVTtULLqapVh0I6LxnTXErvOWs77p1X1jVOWtVIWwM4AQ6FZlICNFZoBczXkttaXJLrw91din9mzJMZQm6x7-2Icc6GC7HUDTS8Kein_9DnOKexfGc4141iimsoFDtQbYo5J-zMLoXBpr8GmNn7N8W_2fs3R_9l5ePx8OwG9K8LL8IL8OEABER8jRull6LUP7tliAA</recordid><startdate>20200101</startdate><enddate>20200101</enddate><creator>Liu, Huanhua</creator><creator>Zhang, Yun</creator><creator>Zhang, Huan</creator><creator>Fan, Chunling</creator><creator>Kwong, Sam</creator><creator>Kuo, C.-C. Jay</creator><creator>Fan, Xiaoping</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0001-9474-5035</orcidid><orcidid>https://orcid.org/0000-0002-5507-4985</orcidid><orcidid>https://orcid.org/0000-0001-7484-7261</orcidid><orcidid>https://orcid.org/0000-0003-0172-4070</orcidid><orcidid>https://orcid.org/0000-0001-9457-7801</orcidid></search><sort><creationdate>20200101</creationdate><title>Deep Learning-Based Picture-Wise Just Noticeable Distortion Prediction Model for Image Compression</title><author>Liu, Huanhua ; Zhang, Yun ; Zhang, Huan ; Fan, Chunling ; Kwong, Sam ; Kuo, C.-C. Jay ; Fan, Xiaoping</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c394t-57fe34bd4009244dd20cf2dbd7ab8b4a784a511b31be39044118a39710d542a53</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Adaptation models</topic><topic>Bit rate</topic><topic>Classification</topic><topic>Classifiers</topic><topic>convolutional neural network</topic><topic>Deep learning</topic><topic>Distortion</topic><topic>Image coding</topic><topic>Image compression</topic><topic>Image processing</topic><topic>image quality assessment</topic><topic>Just noticeable distortion</topic><topic>Machine learning</topic><topic>Masking</topic><topic>Prediction models</topic><topic>Predictive models</topic><topic>Streaming media</topic><topic>Video</topic><topic>Visual perception</topic><topic>Visualization</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Liu, Huanhua</creatorcontrib><creatorcontrib>Zhang, Yun</creatorcontrib><creatorcontrib>Zhang, Huan</creatorcontrib><creatorcontrib>Fan, Chunling</creatorcontrib><creatorcontrib>Kwong, Sam</creatorcontrib><creatorcontrib>Kuo, C.-C. Jay</creatorcontrib><creatorcontrib>Fan, Xiaoping</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>MEDLINE - Academic</collection><jtitle>IEEE transactions on image processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Liu, Huanhua</au><au>Zhang, Yun</au><au>Zhang, Huan</au><au>Fan, Chunling</au><au>Kwong, Sam</au><au>Kuo, C.-C. Jay</au><au>Fan, Xiaoping</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Deep Learning-Based Picture-Wise Just Noticeable Distortion Prediction Model for Image Compression</atitle><jtitle>IEEE transactions on image processing</jtitle><stitle>TIP</stitle><addtitle>IEEE Trans Image Process</addtitle><date>2020-01-01</date><risdate>2020</risdate><volume>29</volume><spage>641</spage><epage>656</epage><pages>641-656</pages><issn>1057-7149</issn><eissn>1941-0042</eissn><coden>IIPRE4</coden><abstract>Picture Wise Just Noticeable Difference (PW-JND), which accounts for the minimum difference of a picture that human visual system can perceive, can be widely used in perception-oriented image and video processing. However, the conventional Just Noticeable Difference (JND) models calculate the JND threshold for each pixel or sub-band separately, which may not reflect the total masking effect of a picture accurately. In this paper, we propose a deep learning based PW-JND prediction model for image compression. Firstly, we formulate the task of predicting PW-JND as a multi-class classification problem, and propose a framework to transform the multi-class classification problem to a binary classification problem solved by just one binary classifier. Secondly, we construct a deep learning based binary classifier named perceptually lossy/lossless predictor which can predict whether an image is perceptually lossy to another or not. Finally, we propose a sliding window based search strategy to predict PW-JND based on the prediction results of the perceptually lossy/lossless predictor. Experimental results show that the mean accuracy of the perceptually lossy/lossless predictor reaches 92%, and the absolute prediction error of the proposed PW-JND model is 0.79 dB on average, which show the superiority of the proposed PW-JND model to the conventional JND models.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>31425033</pmid><doi>10.1109/TIP.2019.2933743</doi><tpages>16</tpages><orcidid>https://orcid.org/0000-0001-9474-5035</orcidid><orcidid>https://orcid.org/0000-0002-5507-4985</orcidid><orcidid>https://orcid.org/0000-0001-7484-7261</orcidid><orcidid>https://orcid.org/0000-0003-0172-4070</orcidid><orcidid>https://orcid.org/0000-0001-9457-7801</orcidid></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1057-7149
ispartof IEEE transactions on image processing, 2020-01, Vol.29, p.641-656
issn 1057-7149
1941-0042
language eng
recordid cdi_proquest_miscellaneous_2336981828
source IEEE Electronic Library (IEL)
subjects Adaptation models
Bit rate
Classification
Classifiers
convolutional neural network
Deep learning
Distortion
Image coding
Image compression
Image processing
image quality assessment
Just noticeable distortion
Machine learning
Masking
Prediction models
Predictive models
Streaming media
Video
Visual perception
Visualization
title Deep Learning-Based Picture-Wise Just Noticeable Distortion Prediction Model for Image Compression
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T07%3A27%3A55IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Deep%20Learning-Based%20Picture-Wise%20Just%20Noticeable%20Distortion%20Prediction%20Model%20for%20Image%20Compression&rft.jtitle=IEEE%20transactions%20on%20image%20processing&rft.au=Liu,%20Huanhua&rft.date=2020-01-01&rft.volume=29&rft.spage=641&rft.epage=656&rft.pages=641-656&rft.issn=1057-7149&rft.eissn=1941-0042&rft.coden=IIPRE4&rft_id=info:doi/10.1109/TIP.2019.2933743&rft_dat=%3Cproquest_RIE%3E2336981828%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2298707291&rft_id=info:pmid/31425033&rft_ieee_id=8796396&rfr_iscdi=true