Image Quality Assessments By Leveraging Diverse Visual Tasks
Image quality assessment (IQA) is a fundamental task in computer vision with the goal of accurately predicting the mean opinion score of humans for assessing the quality of images. While recent advances in deep neural networks (DNNs) have sparked much research on IQA, with the hope for IQA to mimic...
Gespeichert in:
| Veröffentlicht in: | IEEE access 2025-01, Vol.13, p.1-1 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1 |
|---|---|
| container_issue | |
| container_start_page | 1 |
| container_title | IEEE access |
| container_volume | 13 |
| creator | Lee, Joonhee Park, Dongwon Chun, Se Young |
| description | Image quality assessment (IQA) is a fundamental task in computer vision with the goal of accurately predicting the mean opinion score of humans for assessing the quality of images. While recent advances in deep neural networks (DNNs) have sparked much research on IQA, with the hope for IQA to mimic humans effectively, there has been a lack of systematic and analytical research on understanding what factors humans prioritize during IQA. This paper aims to identify human priorities in image evaluation by leveraging the DNN models for diverse computer vision tasks and proposes simple, but effective IQA metrics through our comprehensive analyses on those models. Then, these analyses led us to propose a novel vision-ensemble IQA (VE-IQA) method that demonstrated superior performance as compared to prior arts in IQA on popular IQA benchmarks such as LIVE, CSIQ, and TID2013. |
| doi_str_mv | 10.1109/ACCESS.2025.3531500 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_ieee_primary_10845170</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10845170</ieee_id><doaj_id>oai_doaj_org_article_e899e5e7a7ba4cb5be753cf5f5cea9d6</doaj_id><sourcerecordid>3161370945</sourcerecordid><originalsourceid>FETCH-LOGICAL-c2040-e966ce69056cc47defbcf5c02fc26525119c83b35b4fbcc8d17021d283d75c0d3</originalsourceid><addsrcrecordid>eNpNUFtLwzAUDqLg0P0CfSj43JlLkzTgy6xTBwORTV9Dmp6WzG2dSSfs35vZIcvLOTn5LjkfQjcEjwjB6n5cFJP5fEQx5SPGGeEYn6EBJUKl8SrOT_pLNAxhiePJ44jLAXqYrk0DyfvOrFy3T8YhQAhr2HQhedwnM_gBbxq3aZInF9sAyacLEZssTPgK1-iiNqsAw2O9Qh_Pk0Xxms7eXqbFeJZaijOcghLCglCYC2szWUFd2ppbTGtLBaecEGVzVjJeZvHF5hWRmJKK5qySEVaxKzTtdavWLPXWu7Xxe90ap_8GrW-08Z2zK9CQKwUcpJGlyWzJS5CcRbfoB0ZVImrd9Vpb337vIHR62e78Jn5fMyIIk1hlPKJYj7K-DcFD_e9KsD6krvvU9SF1fUw9sm57lgOAE0ae8bgS-wVGvn1m</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3161370945</pqid></control><display><type>article</type><title>Image Quality Assessments By Leveraging Diverse Visual Tasks</title><source>IEEE Open Access Journals</source><source>DOAJ Directory of Open Access Journals</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Lee, Joonhee ; Park, Dongwon ; Chun, Se Young</creator><creatorcontrib>Lee, Joonhee ; Park, Dongwon ; Chun, Se Young</creatorcontrib><description>Image quality assessment (IQA) is a fundamental task in computer vision with the goal of accurately predicting the mean opinion score of humans for assessing the quality of images. While recent advances in deep neural networks (DNNs) have sparked much research on IQA, with the hope for IQA to mimic humans effectively, there has been a lack of systematic and analytical research on understanding what factors humans prioritize during IQA. This paper aims to identify human priorities in image evaluation by leveraging the DNN models for diverse computer vision tasks and proposes simple, but effective IQA metrics through our comprehensive analyses on those models. Then, these analyses led us to propose a novel vision-ensemble IQA (VE-IQA) method that demonstrated superior performance as compared to prior arts in IQA on popular IQA benchmarks such as LIVE, CSIQ, and TID2013.</description><identifier>ISSN: 2169-3536</identifier><identifier>EISSN: 2169-3536</identifier><identifier>DOI: 10.1109/ACCESS.2025.3531500</identifier><identifier>CODEN: IAECCG</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Artificial neural networks ; Computer vision ; Correlation ; diverse visual tasks ; Feature extraction ; Fitting ; Image edge detection ; Image quality ; Image quality assessment ; Measurement ; Quality assessment ; Scene classification ; Training ; Transfer learning ; vision-ensemble ; Visual tasks ; Visualization</subject><ispartof>IEEE access, 2025-01, Vol.13, p.1-1</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c2040-e966ce69056cc47defbcf5c02fc26525119c83b35b4fbcc8d17021d283d75c0d3</cites><orcidid>0000-0001-8739-8960 ; 0009-0003-6056-4967</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10845170$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,776,780,860,2096,27610,27901,27902,54908</link.rule.ids></links><search><creatorcontrib>Lee, Joonhee</creatorcontrib><creatorcontrib>Park, Dongwon</creatorcontrib><creatorcontrib>Chun, Se Young</creatorcontrib><title>Image Quality Assessments By Leveraging Diverse Visual Tasks</title><title>IEEE access</title><addtitle>Access</addtitle><description>Image quality assessment (IQA) is a fundamental task in computer vision with the goal of accurately predicting the mean opinion score of humans for assessing the quality of images. While recent advances in deep neural networks (DNNs) have sparked much research on IQA, with the hope for IQA to mimic humans effectively, there has been a lack of systematic and analytical research on understanding what factors humans prioritize during IQA. This paper aims to identify human priorities in image evaluation by leveraging the DNN models for diverse computer vision tasks and proposes simple, but effective IQA metrics through our comprehensive analyses on those models. Then, these analyses led us to propose a novel vision-ensemble IQA (VE-IQA) method that demonstrated superior performance as compared to prior arts in IQA on popular IQA benchmarks such as LIVE, CSIQ, and TID2013.</description><subject>Artificial neural networks</subject><subject>Computer vision</subject><subject>Correlation</subject><subject>diverse visual tasks</subject><subject>Feature extraction</subject><subject>Fitting</subject><subject>Image edge detection</subject><subject>Image quality</subject><subject>Image quality assessment</subject><subject>Measurement</subject><subject>Quality assessment</subject><subject>Scene classification</subject><subject>Training</subject><subject>Transfer learning</subject><subject>vision-ensemble</subject><subject>Visual tasks</subject><subject>Visualization</subject><issn>2169-3536</issn><issn>2169-3536</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2025</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>RIE</sourceid><sourceid>DOA</sourceid><recordid>eNpNUFtLwzAUDqLg0P0CfSj43JlLkzTgy6xTBwORTV9Dmp6WzG2dSSfs35vZIcvLOTn5LjkfQjcEjwjB6n5cFJP5fEQx5SPGGeEYn6EBJUKl8SrOT_pLNAxhiePJ44jLAXqYrk0DyfvOrFy3T8YhQAhr2HQhedwnM_gBbxq3aZInF9sAyacLEZssTPgK1-iiNqsAw2O9Qh_Pk0Xxms7eXqbFeJZaijOcghLCglCYC2szWUFd2ppbTGtLBaecEGVzVjJeZvHF5hWRmJKK5qySEVaxKzTtdavWLPXWu7Xxe90ap_8GrW-08Z2zK9CQKwUcpJGlyWzJS5CcRbfoB0ZVImrd9Vpb337vIHR62e78Jn5fMyIIk1hlPKJYj7K-DcFD_e9KsD6krvvU9SF1fUw9sm57lgOAE0ae8bgS-wVGvn1m</recordid><startdate>20250101</startdate><enddate>20250101</enddate><creator>Lee, Joonhee</creator><creator>Park, Dongwon</creator><creator>Chun, Se Young</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7SR</scope><scope>8BQ</scope><scope>8FD</scope><scope>JG9</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0001-8739-8960</orcidid><orcidid>https://orcid.org/0009-0003-6056-4967</orcidid></search><sort><creationdate>20250101</creationdate><title>Image Quality Assessments By Leveraging Diverse Visual Tasks</title><author>Lee, Joonhee ; Park, Dongwon ; Chun, Se Young</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c2040-e966ce69056cc47defbcf5c02fc26525119c83b35b4fbcc8d17021d283d75c0d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2025</creationdate><topic>Artificial neural networks</topic><topic>Computer vision</topic><topic>Correlation</topic><topic>diverse visual tasks</topic><topic>Feature extraction</topic><topic>Fitting</topic><topic>Image edge detection</topic><topic>Image quality</topic><topic>Image quality assessment</topic><topic>Measurement</topic><topic>Quality assessment</topic><topic>Scene classification</topic><topic>Training</topic><topic>Transfer learning</topic><topic>vision-ensemble</topic><topic>Visual tasks</topic><topic>Visualization</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lee, Joonhee</creatorcontrib><creatorcontrib>Park, Dongwon</creatorcontrib><creatorcontrib>Chun, Se Young</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>Materials 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>DOAJ Directory of Open Access Journals</collection><jtitle>IEEE access</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lee, Joonhee</au><au>Park, Dongwon</au><au>Chun, Se Young</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Image Quality Assessments By Leveraging Diverse Visual Tasks</atitle><jtitle>IEEE access</jtitle><stitle>Access</stitle><date>2025-01-01</date><risdate>2025</risdate><volume>13</volume><spage>1</spage><epage>1</epage><pages>1-1</pages><issn>2169-3536</issn><eissn>2169-3536</eissn><coden>IAECCG</coden><abstract>Image quality assessment (IQA) is a fundamental task in computer vision with the goal of accurately predicting the mean opinion score of humans for assessing the quality of images. While recent advances in deep neural networks (DNNs) have sparked much research on IQA, with the hope for IQA to mimic humans effectively, there has been a lack of systematic and analytical research on understanding what factors humans prioritize during IQA. This paper aims to identify human priorities in image evaluation by leveraging the DNN models for diverse computer vision tasks and proposes simple, but effective IQA metrics through our comprehensive analyses on those models. Then, these analyses led us to propose a novel vision-ensemble IQA (VE-IQA) method that demonstrated superior performance as compared to prior arts in IQA on popular IQA benchmarks such as LIVE, CSIQ, and TID2013.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/ACCESS.2025.3531500</doi><tpages>1</tpages><orcidid>https://orcid.org/0000-0001-8739-8960</orcidid><orcidid>https://orcid.org/0009-0003-6056-4967</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2169-3536 |
| ispartof | IEEE access, 2025-01, Vol.13, p.1-1 |
| issn | 2169-3536 2169-3536 |
| language | eng |
| recordid | cdi_ieee_primary_10845170 |
| source | IEEE Open Access Journals; DOAJ Directory of Open Access Journals; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals |
| subjects | Artificial neural networks Computer vision Correlation diverse visual tasks Feature extraction Fitting Image edge detection Image quality Image quality assessment Measurement Quality assessment Scene classification Training Transfer learning vision-ensemble Visual tasks Visualization |
| title | Image Quality Assessments By Leveraging Diverse Visual Tasks |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-11T04%3A40%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Image%20Quality%20Assessments%20By%20Leveraging%20Diverse%20Visual%20Tasks&rft.jtitle=IEEE%20access&rft.au=Lee,%20Joonhee&rft.date=2025-01-01&rft.volume=13&rft.spage=1&rft.epage=1&rft.pages=1-1&rft.issn=2169-3536&rft.eissn=2169-3536&rft.coden=IAECCG&rft_id=info:doi/10.1109/ACCESS.2025.3531500&rft_dat=%3Cproquest_ieee_%3E3161370945%3C/proquest_ieee_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3161370945&rft_id=info:pmid/&rft_ieee_id=10845170&rft_doaj_id=oai_doaj_org_article_e899e5e7a7ba4cb5be753cf5f5cea9d6&rfr_iscdi=true |