Loading…
Indexing using a spectral encoding of topological structure
In an object recognition system, if the extracted image features are multilevel or multiscale, the indexing structure may take the form of a tree. Such structures are not only common in computer vision, but also appear in linguistics, graphics, computational biology, and a wide range of other domain...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 497 Vol. 2 |
| container_issue | |
| container_start_page | 491 |
| container_title | |
| container_volume | 2 |
| creator | Shokoufandeh, A. Dickinson, S.J. Siddiqi, K. Zucker, S.W. |
| description | In an object recognition system, if the extracted image features are multilevel or multiscale, the indexing structure may take the form of a tree. Such structures are not only common in computer vision, but also appear in linguistics, graphics, computational biology, and a wide range of other domains. In this paper, we develop an indexing mechanism that maps the topological structure of a tree into a low-dimensional vector space. Based on a novel eigenvalue characterization of a tree, this topological signature allows us to efficiently retrieve a small set of candidates from a database of models. To accommodate occlusion and local deformation, local evidence is accumulated in each of the tree's topological subspaces. We demonstrate the approach with a series of indexing experiments in the domain of 2-D object recognition. |
| doi_str_mv | 10.1109/CVPR.1999.784726 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_784726</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>784726</ieee_id><sourcerecordid>784726</sourcerecordid><originalsourceid>FETCH-LOGICAL-i118t-6267d87f0db4af94c2f2e20b5b3a6fe8fe8a6c23baeb8d569388aaa21de1d9ff3</originalsourceid><addsrcrecordid>eNotj1FLwzAUhQMqOOfexaf-gdbcpE1y8UmKzsFAEfV1pMnNqNS2JC3ov3djwuE78D0cOIzdAC8AON7Vn69vBSBioU2phTpjK9SGa4UVhxLxnC2AK5krBLxkVyl9cS6kFnzB7je9p5-232dzOtJmaSQ3Rdtl1LvBH90QsmkYh27Yt-7g0xRnN82RrtlFsF2i1X8v2cfT43v9nG9f1pv6YZu3AGbKlVDaGx24b0obsHQiCBK8qRppVSBziFVOyMZSY3ylUBpjrRXgCTyGIJfs9rTbEtFujO23jb-701X5B20JST8</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Indexing using a spectral encoding of topological structure</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Shokoufandeh, A. ; Dickinson, S.J. ; Siddiqi, K. ; Zucker, S.W.</creator><creatorcontrib>Shokoufandeh, A. ; Dickinson, S.J. ; Siddiqi, K. ; Zucker, S.W.</creatorcontrib><description>In an object recognition system, if the extracted image features are multilevel or multiscale, the indexing structure may take the form of a tree. Such structures are not only common in computer vision, but also appear in linguistics, graphics, computational biology, and a wide range of other domains. In this paper, we develop an indexing mechanism that maps the topological structure of a tree into a low-dimensional vector space. Based on a novel eigenvalue characterization of a tree, this topological signature allows us to efficiently retrieve a small set of candidates from a database of models. To accommodate occlusion and local deformation, local evidence is accumulated in each of the tree's topological subspaces. We demonstrate the approach with a series of indexing experiments in the domain of 2-D object recognition.</description><identifier>ISSN: 1063-6919</identifier><identifier>ISBN: 9780769501499</identifier><identifier>ISBN: 0769501494</identifier><identifier>DOI: 10.1109/CVPR.1999.784726</identifier><language>eng</language><publisher>IEEE</publisher><subject>Computational biology ; Computer graphics ; Computer vision ; Eigenvalues and eigenfunctions ; Encoding ; Feature extraction ; Indexing ; Information retrieval ; Object recognition ; Tree graphs</subject><ispartof>Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), 1999, Vol.2, p.491-497 Vol. 2</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/784726$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,4050,4051,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/784726$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Shokoufandeh, A.</creatorcontrib><creatorcontrib>Dickinson, S.J.</creatorcontrib><creatorcontrib>Siddiqi, K.</creatorcontrib><creatorcontrib>Zucker, S.W.</creatorcontrib><title>Indexing using a spectral encoding of topological structure</title><title>Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)</title><addtitle>CVPR</addtitle><description>In an object recognition system, if the extracted image features are multilevel or multiscale, the indexing structure may take the form of a tree. Such structures are not only common in computer vision, but also appear in linguistics, graphics, computational biology, and a wide range of other domains. In this paper, we develop an indexing mechanism that maps the topological structure of a tree into a low-dimensional vector space. Based on a novel eigenvalue characterization of a tree, this topological signature allows us to efficiently retrieve a small set of candidates from a database of models. To accommodate occlusion and local deformation, local evidence is accumulated in each of the tree's topological subspaces. We demonstrate the approach with a series of indexing experiments in the domain of 2-D object recognition.</description><subject>Computational biology</subject><subject>Computer graphics</subject><subject>Computer vision</subject><subject>Eigenvalues and eigenfunctions</subject><subject>Encoding</subject><subject>Feature extraction</subject><subject>Indexing</subject><subject>Information retrieval</subject><subject>Object recognition</subject><subject>Tree graphs</subject><issn>1063-6919</issn><isbn>9780769501499</isbn><isbn>0769501494</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>1999</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj1FLwzAUhQMqOOfexaf-gdbcpE1y8UmKzsFAEfV1pMnNqNS2JC3ov3djwuE78D0cOIzdAC8AON7Vn69vBSBioU2phTpjK9SGa4UVhxLxnC2AK5krBLxkVyl9cS6kFnzB7je9p5-232dzOtJmaSQ3Rdtl1LvBH90QsmkYh27Yt-7g0xRnN82RrtlFsF2i1X8v2cfT43v9nG9f1pv6YZu3AGbKlVDaGx24b0obsHQiCBK8qRppVSBziFVOyMZSY3ylUBpjrRXgCTyGIJfs9rTbEtFujO23jb-701X5B20JST8</recordid><startdate>1999</startdate><enddate>1999</enddate><creator>Shokoufandeh, A.</creator><creator>Dickinson, S.J.</creator><creator>Siddiqi, K.</creator><creator>Zucker, S.W.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>1999</creationdate><title>Indexing using a spectral encoding of topological structure</title><author>Shokoufandeh, A. ; Dickinson, S.J. ; Siddiqi, K. ; Zucker, S.W.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i118t-6267d87f0db4af94c2f2e20b5b3a6fe8fe8a6c23baeb8d569388aaa21de1d9ff3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>1999</creationdate><topic>Computational biology</topic><topic>Computer graphics</topic><topic>Computer vision</topic><topic>Eigenvalues and eigenfunctions</topic><topic>Encoding</topic><topic>Feature extraction</topic><topic>Indexing</topic><topic>Information retrieval</topic><topic>Object recognition</topic><topic>Tree graphs</topic><toplevel>online_resources</toplevel><creatorcontrib>Shokoufandeh, A.</creatorcontrib><creatorcontrib>Dickinson, S.J.</creatorcontrib><creatorcontrib>Siddiqi, K.</creatorcontrib><creatorcontrib>Zucker, S.W.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore (Online service)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Shokoufandeh, A.</au><au>Dickinson, S.J.</au><au>Siddiqi, K.</au><au>Zucker, S.W.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Indexing using a spectral encoding of topological structure</atitle><btitle>Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)</btitle><stitle>CVPR</stitle><date>1999</date><risdate>1999</risdate><volume>2</volume><spage>491</spage><epage>497 Vol. 2</epage><pages>491-497 Vol. 2</pages><issn>1063-6919</issn><isbn>9780769501499</isbn><isbn>0769501494</isbn><abstract>In an object recognition system, if the extracted image features are multilevel or multiscale, the indexing structure may take the form of a tree. Such structures are not only common in computer vision, but also appear in linguistics, graphics, computational biology, and a wide range of other domains. In this paper, we develop an indexing mechanism that maps the topological structure of a tree into a low-dimensional vector space. Based on a novel eigenvalue characterization of a tree, this topological signature allows us to efficiently retrieve a small set of candidates from a database of models. To accommodate occlusion and local deformation, local evidence is accumulated in each of the tree's topological subspaces. We demonstrate the approach with a series of indexing experiments in the domain of 2-D object recognition.</abstract><pub>IEEE</pub><doi>10.1109/CVPR.1999.784726</doi></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1063-6919 |
| ispartof | Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), 1999, Vol.2, p.491-497 Vol. 2 |
| issn | 1063-6919 |
| language | eng |
| recordid | cdi_ieee_primary_784726 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Computational biology Computer graphics Computer vision Eigenvalues and eigenfunctions Encoding Feature extraction Indexing Information retrieval Object recognition Tree graphs |
| title | Indexing using a spectral encoding of topological structure |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T07%3A39%3A28IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Indexing%20using%20a%20spectral%20encoding%20of%20topological%20structure&rft.btitle=Proceedings.%201999%20IEEE%20Computer%20Society%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20(Cat.%20No%20PR00149)&rft.au=Shokoufandeh,%20A.&rft.date=1999&rft.volume=2&rft.spage=491&rft.epage=497%20Vol.%202&rft.pages=491-497%20Vol.%202&rft.issn=1063-6919&rft.isbn=9780769501499&rft.isbn_list=0769501494&rft_id=info:doi/10.1109/CVPR.1999.784726&rft_dat=%3Cieee_6IE%3E784726%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i118t-6267d87f0db4af94c2f2e20b5b3a6fe8fe8a6c23baeb8d569388aaa21de1d9ff3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=784726&rfr_iscdi=true |