Measuring GNG Topology Preservation in Computer Vision Applications

Self-organizing neural networks try to preserve the topology of an input space by means of their competitive learning. This capacity has been used, among others, for the representation of objects and their motion. In addition, these applications usually have real-time constraints. In this work we ha...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Rodríguez, José García, Flórez-Revuelta, Francisco, Chamizo, Juan Manuel García
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 431
container_issue
container_start_page 424
container_title
container_volume
creator Rodríguez, José García
Flórez-Revuelta, Francisco
Chamizo, Juan Manuel García
description Self-organizing neural networks try to preserve the topology of an input space by means of their competitive learning. This capacity has been used, among others, for the representation of objects and their motion. In addition, these applications usually have real-time constraints. In this work we have study a kind of self-organizing network, the Growing Neural Gas with different parameters, to represent different objects. In some cases, topology preservation is lost and, therefore, the quality of the representation. So, we have made a study to quantify topology preservation to establish the most suitable learning parameters, depending on the kind of objects to represent and the size of the network.
doi_str_mv 10.1007/11893011_54
format Conference Proceeding
fullrecord <record><control><sourceid>pascalfrancis_sprin</sourceid><recordid>TN_cdi_pascalfrancis_primary_19970342</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>19970342</sourcerecordid><originalsourceid>FETCH-LOGICAL-p219t-362d231642e76ab1923bf821e685f01f8b58550d9abcc6e350ae9d78ce77b6833</originalsourceid><addsrcrecordid>eNpNkE1Lw0AYhNcvsK09-Qdy8eAh-r77vccSahXqx6F6DZt0U1bTZNlthf57rVXwNDDzMDBDyCXCDQKoW0RtGCCWgh-RsVGaCQ5cCs7VMRmgRMwZ4-aEDP8CiqdkAAxobhRn52SY0jsAUGXogBSPzqZt9N0qmz3NskUf-rZf7bKX6JKLn3bj-y7zXVb067DduJi9-bS3JiG0vv6J0wU5a2yb3PhXR-T1broo7vP58-yhmMzzQNFscibpkjKUnDolbYWGsqrRFJ3UogFsdCW0ELA0tqpr6ZgA68xS6dopVUnN2IhcHXqDTbVtm2i72qcyRL-2cVeiMQoYp9_c9YFLYT_MxbLq-49UIpT7C8t_F7Iv42Fdfg</addsrcrecordid><sourcetype>Index Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Measuring GNG Topology Preservation in Computer Vision Applications</title><source>Springer Books</source><creator>Rodríguez, José García ; Flórez-Revuelta, Francisco ; Chamizo, Juan Manuel García</creator><contributor>Gabrys, Bogdan ; Jain, Lakhmi C. ; Howlett, Robert J.</contributor><creatorcontrib>Rodríguez, José García ; Flórez-Revuelta, Francisco ; Chamizo, Juan Manuel García ; Gabrys, Bogdan ; Jain, Lakhmi C. ; Howlett, Robert J.</creatorcontrib><description>Self-organizing neural networks try to preserve the topology of an input space by means of their competitive learning. This capacity has been used, among others, for the representation of objects and their motion. In addition, these applications usually have real-time constraints. In this work we have study a kind of self-organizing network, the Growing Neural Gas with different parameters, to represent different objects. In some cases, topology preservation is lost and, therefore, the quality of the representation. So, we have made a study to quantify topology preservation to establish the most suitable learning parameters, depending on the kind of objects to represent and the size of the network.</description><identifier>ISSN: 0302-9743</identifier><identifier>ISBN: 3540465421</identifier><identifier>ISBN: 9783540465423</identifier><identifier>ISBN: 3540465359</identifier><identifier>ISBN: 9783540465355</identifier><identifier>EISSN: 1611-3349</identifier><identifier>EISBN: 9783540465447</identifier><identifier>EISBN: 3540465448</identifier><identifier>DOI: 10.1007/11893011_54</identifier><language>eng</language><publisher>Berlin, Heidelberg: Springer Berlin Heidelberg</publisher><subject>Applied sciences ; Artificial intelligence ; Competitive Learning ; Computer science; control theory; systems ; Computer Vision Application ; Exact sciences and technology ; Gesture Recognition ; Hand Gesture Recognition ; Information systems. Data bases ; Input Space ; Memory organisation. Data processing ; Pattern recognition. Digital image processing. Computational geometry ; Software</subject><ispartof>Knowledge-Based Intelligent Information and Engineering Systems, 2006, p.424-431</ispartof><rights>Springer-Verlag Berlin Heidelberg 2006</rights><rights>2008 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/11893011_54$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/11893011_54$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>309,310,779,780,784,789,790,793,4050,4051,27925,38255,41442,42511</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&amp;idt=19970342$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><contributor>Gabrys, Bogdan</contributor><contributor>Jain, Lakhmi C.</contributor><contributor>Howlett, Robert J.</contributor><creatorcontrib>Rodríguez, José García</creatorcontrib><creatorcontrib>Flórez-Revuelta, Francisco</creatorcontrib><creatorcontrib>Chamizo, Juan Manuel García</creatorcontrib><title>Measuring GNG Topology Preservation in Computer Vision Applications</title><title>Knowledge-Based Intelligent Information and Engineering Systems</title><description>Self-organizing neural networks try to preserve the topology of an input space by means of their competitive learning. This capacity has been used, among others, for the representation of objects and their motion. In addition, these applications usually have real-time constraints. In this work we have study a kind of self-organizing network, the Growing Neural Gas with different parameters, to represent different objects. In some cases, topology preservation is lost and, therefore, the quality of the representation. So, we have made a study to quantify topology preservation to establish the most suitable learning parameters, depending on the kind of objects to represent and the size of the network.</description><subject>Applied sciences</subject><subject>Artificial intelligence</subject><subject>Competitive Learning</subject><subject>Computer science; control theory; systems</subject><subject>Computer Vision Application</subject><subject>Exact sciences and technology</subject><subject>Gesture Recognition</subject><subject>Hand Gesture Recognition</subject><subject>Information systems. Data bases</subject><subject>Input Space</subject><subject>Memory organisation. Data processing</subject><subject>Pattern recognition. Digital image processing. Computational geometry</subject><subject>Software</subject><issn>0302-9743</issn><issn>1611-3349</issn><isbn>3540465421</isbn><isbn>9783540465423</isbn><isbn>3540465359</isbn><isbn>9783540465355</isbn><isbn>9783540465447</isbn><isbn>3540465448</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2006</creationdate><recordtype>conference_proceeding</recordtype><recordid>eNpNkE1Lw0AYhNcvsK09-Qdy8eAh-r77vccSahXqx6F6DZt0U1bTZNlthf57rVXwNDDzMDBDyCXCDQKoW0RtGCCWgh-RsVGaCQ5cCs7VMRmgRMwZ4-aEDP8CiqdkAAxobhRn52SY0jsAUGXogBSPzqZt9N0qmz3NskUf-rZf7bKX6JKLn3bj-y7zXVb067DduJi9-bS3JiG0vv6J0wU5a2yb3PhXR-T1broo7vP58-yhmMzzQNFscibpkjKUnDolbYWGsqrRFJ3UogFsdCW0ELA0tqpr6ZgA68xS6dopVUnN2IhcHXqDTbVtm2i72qcyRL-2cVeiMQoYp9_c9YFLYT_MxbLq-49UIpT7C8t_F7Iv42Fdfg</recordid><startdate>2006</startdate><enddate>2006</enddate><creator>Rodríguez, José García</creator><creator>Flórez-Revuelta, Francisco</creator><creator>Chamizo, Juan Manuel García</creator><general>Springer Berlin Heidelberg</general><general>Springer</general><scope>IQODW</scope></search><sort><creationdate>2006</creationdate><title>Measuring GNG Topology Preservation in Computer Vision Applications</title><author>Rodríguez, José García ; Flórez-Revuelta, Francisco ; Chamizo, Juan Manuel García</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-p219t-362d231642e76ab1923bf821e685f01f8b58550d9abcc6e350ae9d78ce77b6833</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2006</creationdate><topic>Applied sciences</topic><topic>Artificial intelligence</topic><topic>Competitive Learning</topic><topic>Computer science; control theory; systems</topic><topic>Computer Vision Application</topic><topic>Exact sciences and technology</topic><topic>Gesture Recognition</topic><topic>Hand Gesture Recognition</topic><topic>Information systems. Data bases</topic><topic>Input Space</topic><topic>Memory organisation. Data processing</topic><topic>Pattern recognition. Digital image processing. Computational geometry</topic><topic>Software</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Rodríguez, José García</creatorcontrib><creatorcontrib>Flórez-Revuelta, Francisco</creatorcontrib><creatorcontrib>Chamizo, Juan Manuel García</creatorcontrib><collection>Pascal-Francis</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Rodríguez, José García</au><au>Flórez-Revuelta, Francisco</au><au>Chamizo, Juan Manuel García</au><au>Gabrys, Bogdan</au><au>Jain, Lakhmi C.</au><au>Howlett, Robert J.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Measuring GNG Topology Preservation in Computer Vision Applications</atitle><btitle>Knowledge-Based Intelligent Information and Engineering Systems</btitle><date>2006</date><risdate>2006</risdate><spage>424</spage><epage>431</epage><pages>424-431</pages><issn>0302-9743</issn><eissn>1611-3349</eissn><isbn>3540465421</isbn><isbn>9783540465423</isbn><isbn>3540465359</isbn><isbn>9783540465355</isbn><eisbn>9783540465447</eisbn><eisbn>3540465448</eisbn><abstract>Self-organizing neural networks try to preserve the topology of an input space by means of their competitive learning. This capacity has been used, among others, for the representation of objects and their motion. In addition, these applications usually have real-time constraints. In this work we have study a kind of self-organizing network, the Growing Neural Gas with different parameters, to represent different objects. In some cases, topology preservation is lost and, therefore, the quality of the representation. So, we have made a study to quantify topology preservation to establish the most suitable learning parameters, depending on the kind of objects to represent and the size of the network.</abstract><cop>Berlin, Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/11893011_54</doi><tpages>8</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0302-9743
ispartof Knowledge-Based Intelligent Information and Engineering Systems, 2006, p.424-431
issn 0302-9743
1611-3349
language eng
recordid cdi_pascalfrancis_primary_19970342
source Springer Books
subjects Applied sciences
Artificial intelligence
Competitive Learning
Computer science
control theory
systems
Computer Vision Application
Exact sciences and technology
Gesture Recognition
Hand Gesture Recognition
Information systems. Data bases
Input Space
Memory organisation. Data processing
Pattern recognition. Digital image processing. Computational geometry
Software
title Measuring GNG Topology Preservation in Computer Vision Applications
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T07%3A22%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-pascalfrancis_sprin&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Measuring%20GNG%20Topology%20Preservation%20in%20Computer%20Vision%20Applications&rft.btitle=Knowledge-Based%20Intelligent%20Information%20and%20Engineering%20Systems&rft.au=Rodr%C3%ADguez,%20Jos%C3%A9%20Garc%C3%ADa&rft.date=2006&rft.spage=424&rft.epage=431&rft.pages=424-431&rft.issn=0302-9743&rft.eissn=1611-3349&rft.isbn=3540465421&rft.isbn_list=9783540465423&rft.isbn_list=3540465359&rft.isbn_list=9783540465355&rft_id=info:doi/10.1007/11893011_54&rft_dat=%3Cpascalfrancis_sprin%3E19970342%3C/pascalfrancis_sprin%3E%3Curl%3E%3C/url%3E&rft.eisbn=9783540465447&rft.eisbn_list=3540465448&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true