A Gibbsian Kohonen Network for Online Arabic Character Recognition
Identifieur interne : 000C92 ( Main/Exploration ); précédent : 000C91; suivant : 000C93A Gibbsian Kohonen Network for Online Arabic Character Recognition
Auteurs : Neila Mezghani [Canada] ; Amar Mitiche [Canada]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2008.
Abstract
Abstract: The purpose of this study is to investigate handwritten online character recognition by Kohonen neural networks which learn class conditional Gibbs densities from training samples. The characters are represented by histograms (empirical distributions) of features. The Kohonen network learning algorithm implements a gradient ascent which maximizes an entropy criterion under constraints. Using a database of handwritten online Arabic characters produced without constraints by a large number of writers, we conducted extensive experiments which show the advantage of this Gibbsian Kohonen network over other classifiers such as a regular Kohonen neural network and a Gibbsian Bayes classifier.
Url:
DOI: 10.1007/978-3-540-89646-3_48
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 001F30
- to stream Istex, to step Curation: 001D97
- to stream Istex, to step Checkpoint: 000759
- to stream Main, to step Merge: 000D04
- to stream Main, to step Curation: 000C92
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">A Gibbsian Kohonen Network for Online Arabic Character Recognition</title><author><name sortKey="Mezghani, Neila" sort="Mezghani, Neila" uniqKey="Mezghani N" first="Neila" last="Mezghani">Neila Mezghani</name></author><author><name sortKey="Mitiche, Amar" sort="Mitiche, Amar" uniqKey="Mitiche A" first="Amar" last="Mitiche">Amar Mitiche</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:5929786BA2D6AF0AB4814787F5BE1F2FFC0520B4</idno><date when="2008" year="2008">2008</date><idno type="doi">10.1007/978-3-540-89646-3_48</idno><idno type="url">https://api.istex.fr/document/5929786BA2D6AF0AB4814787F5BE1F2FFC0520B4/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">001F30</idno><idno type="wicri:Area/Istex/Curation">001D97</idno><idno type="wicri:Area/Istex/Checkpoint">000759</idno><idno type="wicri:doubleKey">0302-9743:2008:Mezghani N:a:gibbsian:kohonen</idno><idno type="wicri:Area/Main/Merge">000D04</idno><idno type="wicri:Area/Main/Curation">000C92</idno><idno type="wicri:Area/Main/Exploration">000C92</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">A Gibbsian Kohonen Network for Online Arabic Character Recognition</title><author><name sortKey="Mezghani, Neila" sort="Mezghani, Neila" uniqKey="Mezghani N" first="Neila" last="Mezghani">Neila Mezghani</name><affiliation wicri:level="3"><country xml:lang="fr">Canada</country><wicri:regionArea>École de technologie supérieure, Montreal</wicri:regionArea><placeName><settlement type="city">Montréal</settlement><region type="state">Québec</region></placeName></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Canada</country></affiliation></author><author><name sortKey="Mitiche, Amar" sort="Mitiche, Amar" uniqKey="Mitiche A" first="Amar" last="Mitiche">Amar Mitiche</name><affiliation wicri:level="3"><country xml:lang="fr">Canada</country><wicri:regionArea>Institut national de la recherche scientifique, INRS-EMT, Montreal</wicri:regionArea><placeName><settlement type="city">Montréal</settlement><region type="state">Québec</region></placeName></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Canada</country></affiliation></author></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>2008</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">5929786BA2D6AF0AB4814787F5BE1F2FFC0520B4</idno><idno type="DOI">10.1007/978-3-540-89646-3_48</idno><idno type="ChapterID">48</idno><idno type="ChapterID">Chap48</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0302-9743</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: The purpose of this study is to investigate handwritten online character recognition by Kohonen neural networks which learn class conditional Gibbs densities from training samples. The characters are represented by histograms (empirical distributions) of features. The Kohonen network learning algorithm implements a gradient ascent which maximizes an entropy criterion under constraints. Using a database of handwritten online Arabic characters produced without constraints by a large number of writers, we conducted extensive experiments which show the advantage of this Gibbsian Kohonen network over other classifiers such as a regular Kohonen neural network and a Gibbsian Bayes classifier.</div></front></TEI><affiliations><list><country><li>Canada</li></country><region><li>Québec</li></region><settlement><li>Montréal</li></settlement></list><tree><country name="Canada"><region name="Québec"><name sortKey="Mezghani, Neila" sort="Mezghani, Neila" uniqKey="Mezghani N" first="Neila" last="Mezghani">Neila Mezghani</name></region><name sortKey="Mezghani, Neila" sort="Mezghani, Neila" uniqKey="Mezghani N" first="Neila" last="Mezghani">Neila Mezghani</name><name sortKey="Mitiche, Amar" sort="Mitiche, Amar" uniqKey="Mitiche A" first="Amar" last="Mitiche">Amar Mitiche</name><name sortKey="Mitiche, Amar" sort="Mitiche, Amar" uniqKey="Mitiche A" first="Amar" last="Mitiche">Amar Mitiche</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000C92 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000C92 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:5929786BA2D6AF0AB4814787F5BE1F2FFC0520B4
|texte= A Gibbsian Kohonen Network for Online Arabic Character Recognition
}}
| This area was generated with Dilib version V0.6.32. |  |