Texton clustering for local classification using scene-context scale
Scene-context plays an important role in scene analysis and object recognition. Among various sources of scene-context, we focus on scene-context scale, which means the effective region size of local context to classify an image pixel in a scene. This paper presents texton clustering for local class...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 30 |
|---|---|
| container_issue | |
| container_start_page | 26 |
| container_title | |
| container_volume | |
| creator | Yousun Kang Akihiro, S. |
| description | Scene-context plays an important role in scene analysis and object recognition. Among various sources of scene-context, we focus on scene-context scale, which means the effective region size of local context to classify an image pixel in a scene. This paper presents texton clustering for local classification using scene-context scale. The scene-context scale can be estimated by the entropy of the leaf node in multi-scale texton forests. The multi-scale texton forests efficiently provide both hierarchical clustering into semantic textons and local classification depending on different scale levels. In our experiments, we use MSRC21 segmentation dataset to assess our clustering algorithm and show that the usage of the scene-context scale improves recognition performance. |
| doi_str_mv | 10.1109/FCV.2013.6485454 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>proquest_6IE</sourceid><recordid>TN_cdi_proquest_miscellaneous_1800440278</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6485454</ieee_id><sourcerecordid>1800440278</sourcerecordid><originalsourceid>FETCH-LOGICAL-i208t-1a026c50e4dc1afb705b6893819bf86633625b522d9b58c3cb04e594531f305f3</originalsourceid><addsrcrecordid>eNpFkM1LxDAQxSMiqOveBS89emmdfDY9SnVVWPCyei1pdiKRbLs2Keh_b2QXvMzwZn7vMQwh1xQqSqG5W7XvFQPKKyW0FFKckEsqVM2lYpSd_gsQ52QZ4ycAZF-dywV52OB3GofChjkmnPzwUbhxKsJoTchDE6N33prkMzPHv3W0OGBpxyFlZ1Ym4BU5cyZEXB77grytHjftc7l-fXpp79elZ6BTSQ0wZSWg2FpqXF-D7JVuuKZN77RSnCsme8nYtumlttz2IFA2QnLqOEjHF-T2kLufxq8ZY-p2Pp8TghlwnGNHNYAQwGqd0ZsD6hGx209-Z6af7vgg_gs6T1hl</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype><pqid>1800440278</pqid></control><display><type>conference_proceeding</type><title>Texton clustering for local classification using scene-context scale</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Yousun Kang ; Akihiro, S.</creator><creatorcontrib>Yousun Kang ; Akihiro, S.</creatorcontrib><description>Scene-context plays an important role in scene analysis and object recognition. Among various sources of scene-context, we focus on scene-context scale, which means the effective region size of local context to classify an image pixel in a scene. This paper presents texton clustering for local classification using scene-context scale. The scene-context scale can be estimated by the entropy of the leaf node in multi-scale texton forests. The multi-scale texton forests efficiently provide both hierarchical clustering into semantic textons and local classification depending on different scale levels. In our experiments, we use MSRC21 segmentation dataset to assess our clustering algorithm and show that the usage of the scene-context scale improves recognition performance.</description><identifier>ISBN: 1467356204</identifier><identifier>ISBN: 9781467356206</identifier><identifier>EISBN: 1467356212</identifier><identifier>EISBN: 9781467356213</identifier><identifier>DOI: 10.1109/FCV.2013.6485454</identifier><language>eng</language><publisher>IEEE</publisher><subject>Accuracy ; Classification ; Clustering ; Computer vision ; Context ; Decision trees ; Entropy ; Forests ; Image classification ; Object recognition ; Scene analysis ; Segmentation ; Semantics ; Vegetation</subject><ispartof>2013 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV2013), 2013, p.26-30</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6485454$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,314,776,780,785,786,2052,27903,27904,54898</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6485454$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Yousun Kang</creatorcontrib><creatorcontrib>Akihiro, S.</creatorcontrib><title>Texton clustering for local classification using scene-context scale</title><title>2013 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV2013)</title><addtitle>FCV</addtitle><description>Scene-context plays an important role in scene analysis and object recognition. Among various sources of scene-context, we focus on scene-context scale, which means the effective region size of local context to classify an image pixel in a scene. This paper presents texton clustering for local classification using scene-context scale. The scene-context scale can be estimated by the entropy of the leaf node in multi-scale texton forests. The multi-scale texton forests efficiently provide both hierarchical clustering into semantic textons and local classification depending on different scale levels. In our experiments, we use MSRC21 segmentation dataset to assess our clustering algorithm and show that the usage of the scene-context scale improves recognition performance.</description><subject>Accuracy</subject><subject>Classification</subject><subject>Clustering</subject><subject>Computer vision</subject><subject>Context</subject><subject>Decision trees</subject><subject>Entropy</subject><subject>Forests</subject><subject>Image classification</subject><subject>Object recognition</subject><subject>Scene analysis</subject><subject>Segmentation</subject><subject>Semantics</subject><subject>Vegetation</subject><isbn>1467356204</isbn><isbn>9781467356206</isbn><isbn>1467356212</isbn><isbn>9781467356213</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2013</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpFkM1LxDAQxSMiqOveBS89emmdfDY9SnVVWPCyei1pdiKRbLs2Keh_b2QXvMzwZn7vMQwh1xQqSqG5W7XvFQPKKyW0FFKckEsqVM2lYpSd_gsQ52QZ4ycAZF-dywV52OB3GofChjkmnPzwUbhxKsJoTchDE6N33prkMzPHv3W0OGBpxyFlZ1Ym4BU5cyZEXB77grytHjftc7l-fXpp79elZ6BTSQ0wZSWg2FpqXF-D7JVuuKZN77RSnCsme8nYtumlttz2IFA2QnLqOEjHF-T2kLufxq8ZY-p2Pp8TghlwnGNHNYAQwGqd0ZsD6hGx209-Z6af7vgg_gs6T1hl</recordid><startdate>201301</startdate><enddate>201301</enddate><creator>Yousun Kang</creator><creator>Akihiro, S.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>201301</creationdate><title>Texton clustering for local classification using scene-context scale</title><author>Yousun Kang ; Akihiro, S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i208t-1a026c50e4dc1afb705b6893819bf86633625b522d9b58c3cb04e594531f305f3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2013</creationdate><topic>Accuracy</topic><topic>Classification</topic><topic>Clustering</topic><topic>Computer vision</topic><topic>Context</topic><topic>Decision trees</topic><topic>Entropy</topic><topic>Forests</topic><topic>Image classification</topic><topic>Object recognition</topic><topic>Scene analysis</topic><topic>Segmentation</topic><topic>Semantics</topic><topic>Vegetation</topic><toplevel>online_resources</toplevel><creatorcontrib>Yousun Kang</creatorcontrib><creatorcontrib>Akihiro, S.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & 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></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Yousun Kang</au><au>Akihiro, S.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Texton clustering for local classification using scene-context scale</atitle><btitle>2013 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV2013)</btitle><stitle>FCV</stitle><date>2013-01</date><risdate>2013</risdate><spage>26</spage><epage>30</epage><pages>26-30</pages><isbn>1467356204</isbn><isbn>9781467356206</isbn><eisbn>1467356212</eisbn><eisbn>9781467356213</eisbn><abstract>Scene-context plays an important role in scene analysis and object recognition. Among various sources of scene-context, we focus on scene-context scale, which means the effective region size of local context to classify an image pixel in a scene. This paper presents texton clustering for local classification using scene-context scale. The scene-context scale can be estimated by the entropy of the leaf node in multi-scale texton forests. The multi-scale texton forests efficiently provide both hierarchical clustering into semantic textons and local classification depending on different scale levels. In our experiments, we use MSRC21 segmentation dataset to assess our clustering algorithm and show that the usage of the scene-context scale improves recognition performance.</abstract><pub>IEEE</pub><doi>10.1109/FCV.2013.6485454</doi><tpages>5</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 1467356204 |
| ispartof | 2013 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV2013), 2013, p.26-30 |
| issn | |
| language | eng |
| recordid | cdi_proquest_miscellaneous_1800440278 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Accuracy Classification Clustering Computer vision Context Decision trees Entropy Forests Image classification Object recognition Scene analysis Segmentation Semantics Vegetation |
| title | Texton clustering for local classification using scene-context scale |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T02%3A16%3A12IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Texton%20clustering%20for%20local%20classification%20using%20scene-context%20scale&rft.btitle=2013%2019th%20Korea-Japan%20Joint%20Workshop%20on%20Frontiers%20of%20Computer%20Vision%20(FCV2013)&rft.au=Yousun%20Kang&rft.date=2013-01&rft.spage=26&rft.epage=30&rft.pages=26-30&rft.isbn=1467356204&rft.isbn_list=9781467356206&rft_id=info:doi/10.1109/FCV.2013.6485454&rft_dat=%3Cproquest_6IE%3E1800440278%3C/proquest_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1467356212&rft.eisbn_list=9781467356213&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1800440278&rft_id=info:pmid/&rft_ieee_id=6485454&rfr_iscdi=true |