A Method for the Analysis of Ambiguous Segmentations of Images
In this correspondence we are interested in how interpretation and context restrictions can guide the analysis of ambiguous segmentations of images in computer vision systems. The final objective is to find image segments that can be interpreted (classified) such that their interpretations do not co...
Gespeichert in:
| Veröffentlicht in: | IEEE Trans. Pattern Anal. Mach. Intell.; (United States) 1986-11, Vol.PAMI-8 (6), p.755-760 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 760 |
|---|---|
| container_issue | 6 |
| container_start_page | 755 |
| container_title | IEEE Trans. Pattern Anal. Mach. Intell.; (United States) |
| container_volume | PAMI-8 |
| creator | Mota, Fernando A. Velasco, Flavio Roberto D. |
| description | In this correspondence we are interested in how interpretation and context restrictions can guide the analysis of ambiguous segmentations of images in computer vision systems. The final objective is to find image segments that can be interpreted (classified) such that their interpretations do not conflict with interpretations given to related segments. In the case that we have several possible labels for each segment, some of this ambiguity can be reduced by means of a relaxation process. In its discrete formulation, the relaxation operator examines pairs of related segments to see if they have incompatible labels, which are then discarded. This process is iterated until only compatible labels are left. In this work a new approach is proposed that considers all possible segmentations resulting from an ambiguous segmentation simultaneously in only one relaxation process. A new relaxation operator is defined that can be applied to ambiguous segmentations. In this way no backtracking is performed, ambiguity is reduced, and the best solution is still retained. The output of the process is a collection of segmentations and interpretations that is hopefully small enough so that each case can be considered separately. |
| doi_str_mv | 10.1109/TPAMI.1986.4767857 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_4767857</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4767857</ieee_id><sourcerecordid>885561882</sourcerecordid><originalsourceid>FETCH-LOGICAL-c376t-35a1ba1bd152a8b5985001dc66124adeaa432021152272b2439a3f51c2e934aa3</originalsourceid><addsrcrecordid>eNo9kE1r3DAQhkVoSLZp_0ACxZRCT7v1SJYsXQomNOlCQgpNz2Isj3dVbCu1tIf8-yrZzcKADu8zH3oYu4RyBVCab4-_mvv1CoxWq6pWtZb1CVuAEWYppDDv2KIExZdac33O3sf4tyyhkqU4Y-cctDKihgX73hT3lLahK_owF2lLRTPh8Bx9LEJfNGPrN7uwi8Vv2ow0JUw-TK_ResQNxQ_stMch0sfDe8H-3Px4vP65vHu4XV83d0snapXyPQhtrg4kR91Ko2U-pnNKAa-wI8RK8JJDjnnNW14Jg6KX4DgZUSGKC_Z5PzfE5G10PpHbujBN5JKVhmulZYa-7qGnOfzbUUx29NHRMOBE-Q9WaykVZB-Z5HvSzSHGmXr7NPsR52cLpX1xa1_d2he39uA2N306jN-1I3XHljeZGfhyADA6HPoZJ-fjkdOgjTEiY1d7zBPRMX3b8h-5Cofy</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>885561882</pqid></control><display><type>article</type><title>A Method for the Analysis of Ambiguous Segmentations of Images</title><source>IEEE Electronic Library (IEL)</source><creator>Mota, Fernando A. ; Velasco, Flavio Roberto D.</creator><creatorcontrib>Mota, Fernando A. ; Velasco, Flavio Roberto D. ; Instituto de Pesquisas Espaciais, C.P. 515, 12200, S.J. Campos, SP</creatorcontrib><description>In this correspondence we are interested in how interpretation and context restrictions can guide the analysis of ambiguous segmentations of images in computer vision systems. The final objective is to find image segments that can be interpreted (classified) such that their interpretations do not conflict with interpretations given to related segments. In the case that we have several possible labels for each segment, some of this ambiguity can be reduced by means of a relaxation process. In its discrete formulation, the relaxation operator examines pairs of related segments to see if they have incompatible labels, which are then discarded. This process is iterated until only compatible labels are left. In this work a new approach is proposed that considers all possible segmentations resulting from an ambiguous segmentation simultaneously in only one relaxation process. A new relaxation operator is defined that can be applied to ambiguous segmentations. In this way no backtracking is performed, ambiguity is reduced, and the best solution is still retained. The output of the process is a collection of segmentations and interpretations that is hopefully small enough so that each case can be considered separately.</description><identifier>ISSN: 0162-8828</identifier><identifier>EISSN: 1939-3539</identifier><identifier>DOI: 10.1109/TPAMI.1986.4767857</identifier><identifier>PMID: 21869371</identifier><identifier>CODEN: ITPIDJ</identifier><language>eng</language><publisher>Los Alamitos, CA: IEEE</publisher><subject>990210 - Supercomputers- (1987-1989) ; Ambiguous segmentation ; Applied sciences ; Artificial intelligence ; COMPUTER GRAPHICS ; Computer science; control theory; systems ; Computer vision ; COMPUTERS ; constraint satisfaction ; DATA PROCESSING ; Exact sciences and technology ; GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE ; Image analysis ; image interpretation ; IMAGE PROCESSING ; Image segmentation ; Information analysis ; Information processing ; Labeling ; Layout ; Lighting ; MATHEMATICAL OPERATORS ; Pattern recognition. Digital image processing. Computational geometry ; PROCESSING ; Radiometry ; RELAXATION ; scene analysis ; scene labeling ; Solid modeling ; VISION</subject><ispartof>IEEE Trans. Pattern Anal. Mach. Intell.; (United States), 1986-11, Vol.PAMI-8 (6), p.755-760</ispartof><rights>1987 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c376t-35a1ba1bd152a8b5985001dc66124adeaa432021152272b2439a3f51c2e934aa3</citedby><cites>FETCH-LOGICAL-c376t-35a1ba1bd152a8b5985001dc66124adeaa432021152272b2439a3f51c2e934aa3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4767857$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,885,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4767857$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=8189993$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/21869371$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink><backlink>$$Uhttps://www.osti.gov/biblio/5928685$$D View this record in Osti.gov$$Hfree_for_read</backlink></links><search><creatorcontrib>Mota, Fernando A.</creatorcontrib><creatorcontrib>Velasco, Flavio Roberto D.</creatorcontrib><creatorcontrib>Instituto de Pesquisas Espaciais, C.P. 515, 12200, S.J. Campos, SP</creatorcontrib><title>A Method for the Analysis of Ambiguous Segmentations of Images</title><title>IEEE Trans. Pattern Anal. Mach. Intell.; (United States)</title><addtitle>TPAMI</addtitle><addtitle>IEEE Trans Pattern Anal Mach Intell</addtitle><description>In this correspondence we are interested in how interpretation and context restrictions can guide the analysis of ambiguous segmentations of images in computer vision systems. The final objective is to find image segments that can be interpreted (classified) such that their interpretations do not conflict with interpretations given to related segments. In the case that we have several possible labels for each segment, some of this ambiguity can be reduced by means of a relaxation process. In its discrete formulation, the relaxation operator examines pairs of related segments to see if they have incompatible labels, which are then discarded. This process is iterated until only compatible labels are left. In this work a new approach is proposed that considers all possible segmentations resulting from an ambiguous segmentation simultaneously in only one relaxation process. A new relaxation operator is defined that can be applied to ambiguous segmentations. In this way no backtracking is performed, ambiguity is reduced, and the best solution is still retained. The output of the process is a collection of segmentations and interpretations that is hopefully small enough so that each case can be considered separately.</description><subject>990210 - Supercomputers- (1987-1989)</subject><subject>Ambiguous segmentation</subject><subject>Applied sciences</subject><subject>Artificial intelligence</subject><subject>COMPUTER GRAPHICS</subject><subject>Computer science; control theory; systems</subject><subject>Computer vision</subject><subject>COMPUTERS</subject><subject>constraint satisfaction</subject><subject>DATA PROCESSING</subject><subject>Exact sciences and technology</subject><subject>GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE</subject><subject>Image analysis</subject><subject>image interpretation</subject><subject>IMAGE PROCESSING</subject><subject>Image segmentation</subject><subject>Information analysis</subject><subject>Information processing</subject><subject>Labeling</subject><subject>Layout</subject><subject>Lighting</subject><subject>MATHEMATICAL OPERATORS</subject><subject>Pattern recognition. Digital image processing. Computational geometry</subject><subject>PROCESSING</subject><subject>Radiometry</subject><subject>RELAXATION</subject><subject>scene analysis</subject><subject>scene labeling</subject><subject>Solid modeling</subject><subject>VISION</subject><issn>0162-8828</issn><issn>1939-3539</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1986</creationdate><recordtype>article</recordtype><recordid>eNo9kE1r3DAQhkVoSLZp_0ACxZRCT7v1SJYsXQomNOlCQgpNz2Isj3dVbCu1tIf8-yrZzcKADu8zH3oYu4RyBVCab4-_mvv1CoxWq6pWtZb1CVuAEWYppDDv2KIExZdac33O3sf4tyyhkqU4Y-cctDKihgX73hT3lLahK_owF2lLRTPh8Bx9LEJfNGPrN7uwi8Vv2ow0JUw-TK_ResQNxQ_stMch0sfDe8H-3Px4vP65vHu4XV83d0snapXyPQhtrg4kR91Ko2U-pnNKAa-wI8RK8JJDjnnNW14Jg6KX4DgZUSGKC_Z5PzfE5G10PpHbujBN5JKVhmulZYa-7qGnOfzbUUx29NHRMOBE-Q9WaykVZB-Z5HvSzSHGmXr7NPsR52cLpX1xa1_d2he39uA2N306jN-1I3XHljeZGfhyADA6HPoZJ-fjkdOgjTEiY1d7zBPRMX3b8h-5Cofy</recordid><startdate>19861101</startdate><enddate>19861101</enddate><creator>Mota, Fernando A.</creator><creator>Velasco, Flavio Roberto D.</creator><general>IEEE</general><general>IEEE Computer Society</general><scope>IQODW</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>OTOTI</scope></search><sort><creationdate>19861101</creationdate><title>A Method for the Analysis of Ambiguous Segmentations of Images</title><author>Mota, Fernando A. ; Velasco, Flavio Roberto D.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c376t-35a1ba1bd152a8b5985001dc66124adeaa432021152272b2439a3f51c2e934aa3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1986</creationdate><topic>990210 - Supercomputers- (1987-1989)</topic><topic>Ambiguous segmentation</topic><topic>Applied sciences</topic><topic>Artificial intelligence</topic><topic>COMPUTER GRAPHICS</topic><topic>Computer science; control theory; systems</topic><topic>Computer vision</topic><topic>COMPUTERS</topic><topic>constraint satisfaction</topic><topic>DATA PROCESSING</topic><topic>Exact sciences and technology</topic><topic>GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE</topic><topic>Image analysis</topic><topic>image interpretation</topic><topic>IMAGE PROCESSING</topic><topic>Image segmentation</topic><topic>Information analysis</topic><topic>Information processing</topic><topic>Labeling</topic><topic>Layout</topic><topic>Lighting</topic><topic>MATHEMATICAL OPERATORS</topic><topic>Pattern recognition. Digital image processing. Computational geometry</topic><topic>PROCESSING</topic><topic>Radiometry</topic><topic>RELAXATION</topic><topic>scene analysis</topic><topic>scene labeling</topic><topic>Solid modeling</topic><topic>VISION</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Mota, Fernando A.</creatorcontrib><creatorcontrib>Velasco, Flavio Roberto D.</creatorcontrib><creatorcontrib>Instituto de Pesquisas Espaciais, C.P. 515, 12200, S.J. Campos, SP</creatorcontrib><collection>Pascal-Francis</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>OSTI.GOV</collection><jtitle>IEEE Trans. Pattern Anal. Mach. Intell.; (United States)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Mota, Fernando A.</au><au>Velasco, Flavio Roberto D.</au><aucorp>Instituto de Pesquisas Espaciais, C.P. 515, 12200, S.J. Campos, SP</aucorp><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Method for the Analysis of Ambiguous Segmentations of Images</atitle><jtitle>IEEE Trans. Pattern Anal. Mach. Intell.; (United States)</jtitle><stitle>TPAMI</stitle><addtitle>IEEE Trans Pattern Anal Mach Intell</addtitle><date>1986-11-01</date><risdate>1986</risdate><volume>PAMI-8</volume><issue>6</issue><spage>755</spage><epage>760</epage><pages>755-760</pages><issn>0162-8828</issn><eissn>1939-3539</eissn><coden>ITPIDJ</coden><abstract>In this correspondence we are interested in how interpretation and context restrictions can guide the analysis of ambiguous segmentations of images in computer vision systems. The final objective is to find image segments that can be interpreted (classified) such that their interpretations do not conflict with interpretations given to related segments. In the case that we have several possible labels for each segment, some of this ambiguity can be reduced by means of a relaxation process. In its discrete formulation, the relaxation operator examines pairs of related segments to see if they have incompatible labels, which are then discarded. This process is iterated until only compatible labels are left. In this work a new approach is proposed that considers all possible segmentations resulting from an ambiguous segmentation simultaneously in only one relaxation process. A new relaxation operator is defined that can be applied to ambiguous segmentations. In this way no backtracking is performed, ambiguity is reduced, and the best solution is still retained. The output of the process is a collection of segmentations and interpretations that is hopefully small enough so that each case can be considered separately.</abstract><cop>Los Alamitos, CA</cop><pub>IEEE</pub><pmid>21869371</pmid><doi>10.1109/TPAMI.1986.4767857</doi><tpages>6</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 0162-8828 |
| ispartof | IEEE Trans. Pattern Anal. Mach. Intell.; (United States), 1986-11, Vol.PAMI-8 (6), p.755-760 |
| issn | 0162-8828 1939-3539 |
| language | eng |
| recordid | cdi_ieee_primary_4767857 |
| source | IEEE Electronic Library (IEL) |
| subjects | 990210 - Supercomputers- (1987-1989) Ambiguous segmentation Applied sciences Artificial intelligence COMPUTER GRAPHICS Computer science control theory systems Computer vision COMPUTERS constraint satisfaction DATA PROCESSING Exact sciences and technology GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE Image analysis image interpretation IMAGE PROCESSING Image segmentation Information analysis Information processing Labeling Layout Lighting MATHEMATICAL OPERATORS Pattern recognition. Digital image processing. Computational geometry PROCESSING Radiometry RELAXATION scene analysis scene labeling Solid modeling VISION |
| title | A Method for the Analysis of Ambiguous Segmentations of Images |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T03%3A15%3A02IST&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=A%20Method%20for%20the%20Analysis%20of%20Ambiguous%20Segmentations%20of%20Images&rft.jtitle=IEEE%20Trans.%20Pattern%20Anal.%20Mach.%20Intell.;%20(United%20States)&rft.au=Mota,%20Fernando%20A.&rft.aucorp=Instituto%20de%20Pesquisas%20Espaciais,%20C.P.%20515,%2012200,%20S.J.%20Campos,%20SP&rft.date=1986-11-01&rft.volume=PAMI-8&rft.issue=6&rft.spage=755&rft.epage=760&rft.pages=755-760&rft.issn=0162-8828&rft.eissn=1939-3539&rft.coden=ITPIDJ&rft_id=info:doi/10.1109/TPAMI.1986.4767857&rft_dat=%3Cproquest_RIE%3E885561882%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=885561882&rft_id=info:pmid/21869371&rft_ieee_id=4767857&rfr_iscdi=true |