InforLorV4, Main, Exploration, bibRecord, 000E41

Integrating vocabulary clustering with spatial relations for symbol recognition

Identifieur interne : 000E41 ( Main/Exploration ); précédent : 000E40; suivant : 000E42

Integrating vocabulary clustering with spatial relations for symbol recognition

Auteurs : K. C. Santosh [France] ; Bart Lamiroy [France] ; Laurent Wendling [France]

Source :

International journal on document analysis and recognition : (Print) [ 1433-2833 ] ; 2014.

RBID : Pascal:14-0199541

Descripteurs français

Pascal (Inist)
- Reconnaissance forme, Vision ordinateur, Classification, Analyse discriminante, Vocabulaire, Analyse spatiale, Sémiologie, Symbole, Défaut forme, Amas, Analyse statistique, Graphe attribué, Analyse amas, Validation croisée, Câblage, ., Apprentissage non supervisé, Recherche image, Recherche par contenu.
Wicri :
- topic : Classification.

English descriptors

KwdEn :
- Attributed graph, Classification, Cluster, Cluster analysis, Computer vision, Content-based retrieval, Cross validation, Discriminant analysis, Form defect, Image retrieval, Pattern recognition, Semiology, Spatial analysis, Statistical analysis, Symbol, Unsupervised learning, Vocabulary, Wiring.

Abstract

This paper develops a structural symbol recognition method with integrated statistical features. It applies spatial organisation descriptors to the identified shape features within a fixed visual vocabulary that compose a symbol. It builds an attributed relational graph expressing the spatial relations between those visual vocabulary elements. In order to adapt the chosen vocabulary features to multiple and possible specialised contexts, we study the pertinence of unsupervised clustering to capture significant shape variations within a vocabulary class and thus refine the discriminative power of the method. This unsupervised clustering relies on cross-validation between several different cluster indices. The resulting approach is capable of determining part of the pertinent vocabulary and significantly increases recognition results with respect to the state-of-the-art. It is experimentally validated on complex electrical wiring diagram symbols.

Affiliations:

Links toward previous steps (curation, corpus...)

to stream PascalFrancis, to step Corpus: 000017
to stream PascalFrancis, to step Curation: 000987
to stream PascalFrancis, to step Checkpoint: 000016
to stream Main, to step Merge: 000E33
to stream Main, to step Curation: 000E41

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Integrating vocabulary clustering with spatial relations for symbol recognition</title>
<author><name sortKey="Santosh, K C" sort="Santosh, K C" uniqKey="Santosh K" first="K. C." last="Santosh">K. C. Santosh</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>LORIA (UMR 7503), Université de Lorraine, Campus Scientifique, BP 239</s1>
<s2>54506 Vandoeuvre-lés-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><region type="region" nuts="2">Grand Est</region>
<region type="old region" nuts="2">Lorraine (région)</region>
<settlement type="city">Vandœuvre-lès-Nancy</settlement>
</placeName>
<orgName type="university">Université de Lorraine</orgName>
</affiliation>
</author>
<author><name sortKey="Lamiroy, Bart" sort="Lamiroy, Bart" uniqKey="Lamiroy B" first="Bart" last="Lamiroy">Bart Lamiroy</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>LORIA (UMR 7503), Université de Lorraine, Campus Scientifique, BP 239</s1>
<s2>54506 Vandoeuvre-lés-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><region type="region" nuts="2">Grand Est</region>
<region type="old region" nuts="2">Lorraine (région)</region>
<settlement type="city">Vandœuvre-lès-Nancy</settlement>
</placeName>
<orgName type="university">Université de Lorraine</orgName>
</affiliation>
</author>
<author><name sortKey="Wendling, Laurent" sort="Wendling, Laurent" uniqKey="Wendling L" first="Laurent" last="Wendling">Laurent Wendling</name>
<affiliation wicri:level="4"><inist:fA14 i1="02"><s1>SIP, LIPADE, Université Paris Descartes (Paris V), 45, rue des Saints-Pères</s1>
<s2>75270 Paris</s2>
<s3>FRA</s3>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><region type="region" nuts="2">Île-de-France</region>
<settlement type="city">Paris</settlement>
</placeName>
<orgName type="university">Université Paris-Descartes</orgName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">14-0199541</idno>
<date when="2014">2014</date>
<idno type="stanalyst">PASCAL 14-0199541 INIST</idno>
<idno type="RBID">Pascal:14-0199541</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000017</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000987</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000016</idno>
<idno type="wicri:explorRef" wicri:stream="PascalFrancis" wicri:step="Checkpoint">000016</idno>
<idno type="wicri:doubleKey">1433-2833:2014:Santosh K:integrating:vocabulary:clustering</idno>
<idno type="wicri:Area/Main/Merge">000E33</idno>
<idno type="wicri:Area/Main/Curation">000E41</idno>
<idno type="wicri:Area/Main/Exploration">000E41</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Integrating vocabulary clustering with spatial relations for symbol recognition</title>
<author><name sortKey="Santosh, K C" sort="Santosh, K C" uniqKey="Santosh K" first="K. C." last="Santosh">K. C. Santosh</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>LORIA (UMR 7503), Université de Lorraine, Campus Scientifique, BP 239</s1>
<s2>54506 Vandoeuvre-lés-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><region type="region" nuts="2">Grand Est</region>
<region type="old region" nuts="2">Lorraine (région)</region>
<settlement type="city">Vandœuvre-lès-Nancy</settlement>
</placeName>
<orgName type="university">Université de Lorraine</orgName>
</affiliation>
</author>
<author><name sortKey="Lamiroy, Bart" sort="Lamiroy, Bart" uniqKey="Lamiroy B" first="Bart" last="Lamiroy">Bart Lamiroy</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>LORIA (UMR 7503), Université de Lorraine, Campus Scientifique, BP 239</s1>
<s2>54506 Vandoeuvre-lés-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><region type="region" nuts="2">Grand Est</region>
<region type="old region" nuts="2">Lorraine (région)</region>
<settlement type="city">Vandœuvre-lès-Nancy</settlement>
</placeName>
<orgName type="university">Université de Lorraine</orgName>
</affiliation>
</author>
<author><name sortKey="Wendling, Laurent" sort="Wendling, Laurent" uniqKey="Wendling L" first="Laurent" last="Wendling">Laurent Wendling</name>
<affiliation wicri:level="4"><inist:fA14 i1="02"><s1>SIP, LIPADE, Université Paris Descartes (Paris V), 45, rue des Saints-Pères</s1>
<s2>75270 Paris</s2>
<s3>FRA</s3>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><region type="region" nuts="2">Île-de-France</region>
<settlement type="city">Paris</settlement>
</placeName>
<orgName type="university">Université Paris-Descartes</orgName>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">International journal on document analysis and recognition : (Print)</title>
<title level="j" type="abbreviated">Int. j. doc. anal. recognit. : (Print)</title>
<idno type="ISSN">1433-2833</idno>
<imprint><date when="2014">2014</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">International journal on document analysis and recognition : (Print)</title>
<title level="j" type="abbreviated">Int. j. doc. anal. recognit. : (Print)</title>
<idno type="ISSN">1433-2833</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Attributed graph</term>
<term>Classification</term>
<term>Cluster</term>
<term>Cluster analysis</term>
<term>Computer vision</term>
<term>Content-based retrieval</term>
<term>Cross validation</term>
<term>Discriminant analysis</term>
<term>Form defect</term>
<term>Image retrieval</term>
<term>Pattern recognition</term>
<term>Semiology</term>
<term>Spatial analysis</term>
<term>Statistical analysis</term>
<term>Symbol</term>
<term>Unsupervised learning</term>
<term>Vocabulary</term>
<term>Wiring</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Reconnaissance forme</term>
<term>Vision ordinateur</term>
<term>Classification</term>
<term>Analyse discriminante</term>
<term>Vocabulaire</term>
<term>Analyse spatiale</term>
<term>Sémiologie</term>
<term>Symbole</term>
<term>Défaut forme</term>
<term>Amas</term>
<term>Analyse statistique</term>
<term>Graphe attribué</term>
<term>Analyse amas</term>
<term>Validation croisée</term>
<term>Câblage</term>
<term>.</term>
<term>Apprentissage non supervisé</term>
<term>Recherche image</term>
<term>Recherche par contenu</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Classification</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">This paper develops a structural symbol recognition method with integrated statistical features. It applies spatial organisation descriptors to the identified shape features within a fixed visual vocabulary that compose a symbol. It builds an attributed relational graph expressing the spatial relations between those visual vocabulary elements. In order to adapt the chosen vocabulary features to multiple and possible specialised contexts, we study the pertinence of unsupervised clustering to capture significant shape variations within a vocabulary class and thus refine the discriminative power of the method. This unsupervised clustering relies on cross-validation between several different cluster indices. The resulting approach is capable of determining part of the pertinent vocabulary and significantly increases recognition results with respect to the state-of-the-art. It is experimentally validated on complex electrical wiring diagram symbols.</div>
</front>
</TEI>
<affiliations><list><country><li>France</li>
</country>
<region><li>Grand Est</li>
<li>Lorraine (région)</li>
<li>Île-de-France</li>
</region>
<settlement><li>Paris</li>
<li>Vandœuvre-lès-Nancy</li>
</settlement>
<orgName><li>Université Paris-Descartes</li>
<li>Université de Lorraine</li>
</orgName>
</list>
<tree><country name="France"><region name="Grand Est"><name sortKey="Santosh, K C" sort="Santosh, K C" uniqKey="Santosh K" first="K. C." last="Santosh">K. C. Santosh</name>
</region>
<name sortKey="Lamiroy, Bart" sort="Lamiroy, Bart" uniqKey="Lamiroy B" first="Bart" last="Lamiroy">Bart Lamiroy</name>
<name sortKey="Wendling, Laurent" sort="Wendling, Laurent" uniqKey="Wendling L" first="Laurent" last="Wendling">Laurent Wendling</name>
</country>
</tree>
</affiliations>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Exploration

HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000E41 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000E41 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Wicri/Lorraine
   |area=    InforLorV4
   |flux=    Main
   |étape=   Exploration
   |type=    RBID
   |clé=     Pascal:14-0199541
   |texte=   Integrating vocabulary clustering with spatial relations for symbol recognition
}}

This area was generated with Dilib version V0.6.33.
Data generation: Mon Jun 10 21:56:28 2019. Site generation: Fri Feb 25 15:29:27 2022

	Serveur d'exploration sur la recherche en informatique en Lorraine
	Attention, ce site est en cours de développement ! Attention, site généré par des moyens informatiques à partir de corpus bruts. Les informations ne sont donc pas validées.

Serveur d'exploration sur la recherche en informatique en Lorraine

Integrating vocabulary clustering with spatial relations for symbol recognition

Integrating vocabulary clustering with spatial relations for symbol recognition

Source :

Descripteurs français

English descriptors

Abstract

Links toward previous steps (curation, corpus...)

Le document en format XML

Pour manipuler ce document sous Unix (Dilib)

Pour mettre un lien sur cette page dans le réseau Wicri