Image Manipulation Quality Assessment

Image quality assessment (IQA) and its computational models play a vital role in modern computer vision applications. Research has traditionally focused on signal distortions arising during image compression and transmission, and their impact on perceived image quality. However, little attention is...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on circuits and systems for video technology 2024-11, p.1-1
Hauptverfasser: Wu, Xinbo, Lou, Jianxun, Wu, Yingying, Liu, Wanan, Rosin, Paul L., Colombo, Gualtiero, Allen, Stuart, Whitaker, Roger, Liu, Hantao
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 1
container_issue
container_start_page 1
container_title IEEE transactions on circuits and systems for video technology
container_volume
creator Wu, Xinbo
Lou, Jianxun
Wu, Yingying
Liu, Wanan
Rosin, Paul L.
Colombo, Gualtiero
Allen, Stuart
Whitaker, Roger
Liu, Hantao
description Image quality assessment (IQA) and its computational models play a vital role in modern computer vision applications. Research has traditionally focused on signal distortions arising during image compression and transmission, and their impact on perceived image quality. However, little attention is paid to image manipulation that alters an image using various filters. With the prevalence of image manipulation in real-life scenarios, it is critical to understand how humans perceive filter-altered images and to develop reliable IQA models capable of automatically assessing the quality of filtered images. In this paper, we build a new IQA database for filter-altered images, comprised of 360 images manipulated by various filters. To ensure the subjective IQA faithfully reflects human visual perception, we conduct a fully-controlled psychovisual experiment. Building upon the ground truth, we propose an innovative deep learning-based no-reference IQA (NR-IQA) model named IMQA that can accurately predict the perceived quality of filter-altered images. This model involves constructing an image filtering-aware module to learn discriminatory features for filter-altered images; and fuses these features with the representations generated by an image quality-aware module. Experimental results demonstrate the superior performance of the proposed IMQA model.
doi_str_mv 10.1109/TCSVT.2024.3504854
format Article
fullrecord <record><control><sourceid>crossref_RIE</sourceid><recordid>TN_cdi_ieee_primary_10764798</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10764798</ieee_id><sourcerecordid>10_1109_TCSVT_2024_3504854</sourcerecordid><originalsourceid>FETCH-LOGICAL-c648-1f00822e7d2463eb0d915e6cbaf7bdb71405fa8ec8bd4b0e5c3e17a94f9b97663</originalsourceid><addsrcrecordid>eNpNz09Lw0AQh-FFFKzVLyAecvGYOLPZfzmWoLVQETF4XXaTWYkkacmmh357W9uDp5nL-4OHsXuEDBGKp6r8_KoyDlxkuQRhpLhgM5TSpJyDvDz8IDE1HOU1u4nxBwCFEXrGHle9-6bkzQ3tdte5qd0MycfOde20TxYxUow9DdMtuwqui3R3vnNWvTxX5Wu6fl-uysU6rZUwKQYAwznphguVk4emQEmq9i5o33iNAmRwhmrjG-GBZJ0TaleIUPhCK5XPGT_N1uMmxpGC3Y5t78a9RbBHp_1z2qPTnp2H6OEUtUT0L9BK6MLkv8jPTxE</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Image Manipulation Quality Assessment</title><source>IEEE Electronic Library (IEL)</source><creator>Wu, Xinbo ; Lou, Jianxun ; Wu, Yingying ; Liu, Wanan ; Rosin, Paul L. ; Colombo, Gualtiero ; Allen, Stuart ; Whitaker, Roger ; Liu, Hantao</creator><creatorcontrib>Wu, Xinbo ; Lou, Jianxun ; Wu, Yingying ; Liu, Wanan ; Rosin, Paul L. ; Colombo, Gualtiero ; Allen, Stuart ; Whitaker, Roger ; Liu, Hantao</creatorcontrib><description>Image quality assessment (IQA) and its computational models play a vital role in modern computer vision applications. Research has traditionally focused on signal distortions arising during image compression and transmission, and their impact on perceived image quality. However, little attention is paid to image manipulation that alters an image using various filters. With the prevalence of image manipulation in real-life scenarios, it is critical to understand how humans perceive filter-altered images and to develop reliable IQA models capable of automatically assessing the quality of filtered images. In this paper, we build a new IQA database for filter-altered images, comprised of 360 images manipulated by various filters. To ensure the subjective IQA faithfully reflects human visual perception, we conduct a fully-controlled psychovisual experiment. Building upon the ground truth, we propose an innovative deep learning-based no-reference IQA (NR-IQA) model named IMQA that can accurately predict the perceived quality of filter-altered images. This model involves constructing an image filtering-aware module to learn discriminatory features for filter-altered images; and fuses these features with the representations generated by an image quality-aware module. Experimental results demonstrate the superior performance of the proposed IMQA model.</description><identifier>ISSN: 1051-8215</identifier><identifier>EISSN: 1558-2205</identifier><identifier>DOI: 10.1109/TCSVT.2024.3504854</identifier><identifier>CODEN: ITCTEM</identifier><language>eng</language><publisher>IEEE</publisher><subject>Circuits and systems ; Computational modeling ; deep learning ; Distortion ; filter-altered ; Filtering algorithms ; Image color analysis ; image manipulation ; Image quality ; Image quality assessment ; Monitoring ; perception ; Quality assessment ; Visualization</subject><ispartof>IEEE transactions on circuits and systems for video technology, 2024-11, p.1-1</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><orcidid>0000-0002-2982-595X ; 0000-0003-4544-3481 ; 0000-0001-6146-2207 ; 0000-0001-5883-8517 ; 0000-0002-4965-3884 ; 0000-0002-8473-1913</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10764798$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10764798$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Wu, Xinbo</creatorcontrib><creatorcontrib>Lou, Jianxun</creatorcontrib><creatorcontrib>Wu, Yingying</creatorcontrib><creatorcontrib>Liu, Wanan</creatorcontrib><creatorcontrib>Rosin, Paul L.</creatorcontrib><creatorcontrib>Colombo, Gualtiero</creatorcontrib><creatorcontrib>Allen, Stuart</creatorcontrib><creatorcontrib>Whitaker, Roger</creatorcontrib><creatorcontrib>Liu, Hantao</creatorcontrib><title>Image Manipulation Quality Assessment</title><title>IEEE transactions on circuits and systems for video technology</title><addtitle>TCSVT</addtitle><description>Image quality assessment (IQA) and its computational models play a vital role in modern computer vision applications. Research has traditionally focused on signal distortions arising during image compression and transmission, and their impact on perceived image quality. However, little attention is paid to image manipulation that alters an image using various filters. With the prevalence of image manipulation in real-life scenarios, it is critical to understand how humans perceive filter-altered images and to develop reliable IQA models capable of automatically assessing the quality of filtered images. In this paper, we build a new IQA database for filter-altered images, comprised of 360 images manipulated by various filters. To ensure the subjective IQA faithfully reflects human visual perception, we conduct a fully-controlled psychovisual experiment. Building upon the ground truth, we propose an innovative deep learning-based no-reference IQA (NR-IQA) model named IMQA that can accurately predict the perceived quality of filter-altered images. This model involves constructing an image filtering-aware module to learn discriminatory features for filter-altered images; and fuses these features with the representations generated by an image quality-aware module. Experimental results demonstrate the superior performance of the proposed IMQA model.</description><subject>Circuits and systems</subject><subject>Computational modeling</subject><subject>deep learning</subject><subject>Distortion</subject><subject>filter-altered</subject><subject>Filtering algorithms</subject><subject>Image color analysis</subject><subject>image manipulation</subject><subject>Image quality</subject><subject>Image quality assessment</subject><subject>Monitoring</subject><subject>perception</subject><subject>Quality assessment</subject><subject>Visualization</subject><issn>1051-8215</issn><issn>1558-2205</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNz09Lw0AQh-FFFKzVLyAecvGYOLPZfzmWoLVQETF4XXaTWYkkacmmh357W9uDp5nL-4OHsXuEDBGKp6r8_KoyDlxkuQRhpLhgM5TSpJyDvDz8IDE1HOU1u4nxBwCFEXrGHle9-6bkzQ3tdte5qd0MycfOde20TxYxUow9DdMtuwqui3R3vnNWvTxX5Wu6fl-uysU6rZUwKQYAwznphguVk4emQEmq9i5o33iNAmRwhmrjG-GBZJ0TaleIUPhCK5XPGT_N1uMmxpGC3Y5t78a9RbBHp_1z2qPTnp2H6OEUtUT0L9BK6MLkv8jPTxE</recordid><startdate>20241121</startdate><enddate>20241121</enddate><creator>Wu, Xinbo</creator><creator>Lou, Jianxun</creator><creator>Wu, Yingying</creator><creator>Liu, Wanan</creator><creator>Rosin, Paul L.</creator><creator>Colombo, Gualtiero</creator><creator>Allen, Stuart</creator><creator>Whitaker, Roger</creator><creator>Liu, Hantao</creator><general>IEEE</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0002-2982-595X</orcidid><orcidid>https://orcid.org/0000-0003-4544-3481</orcidid><orcidid>https://orcid.org/0000-0001-6146-2207</orcidid><orcidid>https://orcid.org/0000-0001-5883-8517</orcidid><orcidid>https://orcid.org/0000-0002-4965-3884</orcidid><orcidid>https://orcid.org/0000-0002-8473-1913</orcidid></search><sort><creationdate>20241121</creationdate><title>Image Manipulation Quality Assessment</title><author>Wu, Xinbo ; Lou, Jianxun ; Wu, Yingying ; Liu, Wanan ; Rosin, Paul L. ; Colombo, Gualtiero ; Allen, Stuart ; Whitaker, Roger ; Liu, Hantao</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c648-1f00822e7d2463eb0d915e6cbaf7bdb71405fa8ec8bd4b0e5c3e17a94f9b97663</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Circuits and systems</topic><topic>Computational modeling</topic><topic>deep learning</topic><topic>Distortion</topic><topic>filter-altered</topic><topic>Filtering algorithms</topic><topic>Image color analysis</topic><topic>image manipulation</topic><topic>Image quality</topic><topic>Image quality assessment</topic><topic>Monitoring</topic><topic>perception</topic><topic>Quality assessment</topic><topic>Visualization</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Wu, Xinbo</creatorcontrib><creatorcontrib>Lou, Jianxun</creatorcontrib><creatorcontrib>Wu, Yingying</creatorcontrib><creatorcontrib>Liu, Wanan</creatorcontrib><creatorcontrib>Rosin, Paul L.</creatorcontrib><creatorcontrib>Colombo, Gualtiero</creatorcontrib><creatorcontrib>Allen, Stuart</creatorcontrib><creatorcontrib>Whitaker, Roger</creatorcontrib><creatorcontrib>Liu, Hantao</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>CrossRef</collection><jtitle>IEEE transactions on circuits and systems for video technology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Wu, Xinbo</au><au>Lou, Jianxun</au><au>Wu, Yingying</au><au>Liu, Wanan</au><au>Rosin, Paul L.</au><au>Colombo, Gualtiero</au><au>Allen, Stuart</au><au>Whitaker, Roger</au><au>Liu, Hantao</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Image Manipulation Quality Assessment</atitle><jtitle>IEEE transactions on circuits and systems for video technology</jtitle><stitle>TCSVT</stitle><date>2024-11-21</date><risdate>2024</risdate><spage>1</spage><epage>1</epage><pages>1-1</pages><issn>1051-8215</issn><eissn>1558-2205</eissn><coden>ITCTEM</coden><abstract>Image quality assessment (IQA) and its computational models play a vital role in modern computer vision applications. Research has traditionally focused on signal distortions arising during image compression and transmission, and their impact on perceived image quality. However, little attention is paid to image manipulation that alters an image using various filters. With the prevalence of image manipulation in real-life scenarios, it is critical to understand how humans perceive filter-altered images and to develop reliable IQA models capable of automatically assessing the quality of filtered images. In this paper, we build a new IQA database for filter-altered images, comprised of 360 images manipulated by various filters. To ensure the subjective IQA faithfully reflects human visual perception, we conduct a fully-controlled psychovisual experiment. Building upon the ground truth, we propose an innovative deep learning-based no-reference IQA (NR-IQA) model named IMQA that can accurately predict the perceived quality of filter-altered images. This model involves constructing an image filtering-aware module to learn discriminatory features for filter-altered images; and fuses these features with the representations generated by an image quality-aware module. Experimental results demonstrate the superior performance of the proposed IMQA model.</abstract><pub>IEEE</pub><doi>10.1109/TCSVT.2024.3504854</doi><tpages>1</tpages><orcidid>https://orcid.org/0000-0002-2982-595X</orcidid><orcidid>https://orcid.org/0000-0003-4544-3481</orcidid><orcidid>https://orcid.org/0000-0001-6146-2207</orcidid><orcidid>https://orcid.org/0000-0001-5883-8517</orcidid><orcidid>https://orcid.org/0000-0002-4965-3884</orcidid><orcidid>https://orcid.org/0000-0002-8473-1913</orcidid></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1051-8215
ispartof IEEE transactions on circuits and systems for video technology, 2024-11, p.1-1
issn 1051-8215
1558-2205
language eng
recordid cdi_ieee_primary_10764798
source IEEE Electronic Library (IEL)
subjects Circuits and systems
Computational modeling
deep learning
Distortion
filter-altered
Filtering algorithms
Image color analysis
image manipulation
Image quality
Image quality assessment
Monitoring
perception
Quality assessment
Visualization
title Image Manipulation Quality Assessment
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T17%3A51%3A32IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Image%20Manipulation%20Quality%20Assessment&rft.jtitle=IEEE%20transactions%20on%20circuits%20and%20systems%20for%20video%20technology&rft.au=Wu,%20Xinbo&rft.date=2024-11-21&rft.spage=1&rft.epage=1&rft.pages=1-1&rft.issn=1051-8215&rft.eissn=1558-2205&rft.coden=ITCTEM&rft_id=info:doi/10.1109/TCSVT.2024.3504854&rft_dat=%3Ccrossref_RIE%3E10_1109_TCSVT_2024_3504854%3C/crossref_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=10764798&rfr_iscdi=true