Cross-learning in analytic word recognition without segmentation
Identifieur interne : 001376 ( Istex/Curation ); précédent : 001375; suivant : 001377Cross-learning in analytic word recognition without segmentation
Auteurs : C. Choisy ; A. BelaïdSource :
- International Journal on Document Analysis and Recognition [ 1433-2833 ] ; 2002-07-01.
English descriptors
Abstract
Abstract.: In this paper a method for analytic handwritten word recognition based on causal Markov random fields is described. The word models are hmms where each state corresponds to a letter modeled by a nshp-hmm (Markov field). The word models are built dynamically. Training is operated using Baum-Welch algorithm where the parameters are reestimated on the generated word models. The segmentation is unnecessary: the system determines itself during training the best repartition of the information within the letter models. First experiments on two real databases of French check amount words give very encouraging results up to 86% for recognition without rejection.
Url:
DOI: 10.1007/s100320200078
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: Pour aller vers cette notice dans l'étape Curation :001393
Links to Exploration step
ISTEX:55280B7BF363C76D9234E01C9077401C57C89EEBCuration
No country items
C. Choisy<affiliation><mods:affiliation>LORIA/CNRS, Campus scientifique, BP 239, 54506 Vandoeuvre-les-Nancy, France; e-mail: {choisy,abelaid}@loria.fr, FR</mods:affiliation>
<wicri:noCountry code="subField">FR</wicri:noCountry>
</affiliation>
<affiliation><mods:affiliation>LORIA/CNRS, Campus scientifique, BP 239, 54506 Vandoeuvre-les-Nancy, France; e-mail: {choisy,abelaid}@loria.fr, FR</mods:affiliation>
<wicri:noCountry code="subField">FR</wicri:noCountry>
</affiliation>
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Cross-learning in analytic word recognition without segmentation</title>
<author><name sortKey="Choisy, C" sort="Choisy, C" uniqKey="Choisy C" first="C." last="Choisy">C. Choisy</name>
<affiliation><mods:affiliation>LORIA/CNRS, Campus scientifique, BP 239, 54506 Vandoeuvre-les-Nancy, France; e-mail: {choisy,abelaid}@loria.fr, FR</mods:affiliation>
<wicri:noCountry code="subField">FR</wicri:noCountry>
</affiliation>
</author>
<author><name sortKey="Belaid, A" sort="Belaid, A" uniqKey="Belaid A" first="A." last="Belaïd">A. Belaïd</name>
<affiliation><mods:affiliation>LORIA/CNRS, Campus scientifique, BP 239, 54506 Vandoeuvre-les-Nancy, France; e-mail: {choisy,abelaid}@loria.fr, FR</mods:affiliation>
<wicri:noCountry code="subField">FR</wicri:noCountry>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:55280B7BF363C76D9234E01C9077401C57C89EEB</idno>
<date when="2002" year="2002">2002</date>
<idno type="doi">10.1007/s100320200078</idno>
<idno type="url">https://api.istex.fr/ark:/67375/VQC-PW28ZHWN-Z/fulltext.pdf</idno>
<idno type="wicri:Area/Istex/Corpus">001393</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">001393</idno>
<idno type="wicri:Area/Istex/Curation">001376</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Cross-learning in analytic word recognition without segmentation</title>
<author><name sortKey="Choisy, C" sort="Choisy, C" uniqKey="Choisy C" first="C." last="Choisy">C. Choisy</name>
<affiliation><mods:affiliation>LORIA/CNRS, Campus scientifique, BP 239, 54506 Vandoeuvre-les-Nancy, France; e-mail: {choisy,abelaid}@loria.fr, FR</mods:affiliation>
<wicri:noCountry code="subField">FR</wicri:noCountry>
</affiliation>
</author>
<author><name sortKey="Belaid, A" sort="Belaid, A" uniqKey="Belaid A" first="A." last="Belaïd">A. Belaïd</name>
<affiliation><mods:affiliation>LORIA/CNRS, Campus scientifique, BP 239, 54506 Vandoeuvre-les-Nancy, France; e-mail: {choisy,abelaid}@loria.fr, FR</mods:affiliation>
<wicri:noCountry code="subField">FR</wicri:noCountry>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="j">International Journal on Document Analysis and Recognition</title>
<title level="j" type="abbrev">IJDAR</title>
<idno type="ISSN">1433-2833</idno>
<imprint><publisher>Springer-Verlag</publisher>
<pubPlace>Berlin/Heidelberg</pubPlace>
<date type="published" when="2002-07-01">2002-07-01</date>
<biblScope unit="volume">4</biblScope>
<biblScope unit="issue">4</biblScope>
<biblScope unit="page" from="281">281</biblScope>
<biblScope unit="page" to="289">289</biblScope>
</imprint>
<idno type="ISSN">1433-2833</idno>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">1433-2833</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Key words:hmm, nshp-hmm, Cross-learning, Meta-models, Baum-Welch Algorithm</term>
</keywords>
</textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Abstract.: In this paper a method for analytic handwritten word recognition based on causal Markov random fields is described. The word models are hmms where each state corresponds to a letter modeled by a nshp-hmm (Markov field). The word models are built dynamically. Training is operated using Baum-Welch algorithm where the parameters are reestimated on the generated word models. The segmentation is unnecessary: the system determines itself during training the best repartition of the information within the letter models. First experiments on two real databases of French check amount words give very encouraging results up to 86% for recognition without rejection.</div>
</front>
</TEI>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Istex/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001376 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Curation/biblio.hfd -nk 001376 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Istex |étape= Curation |type= RBID |clé= ISTEX:55280B7BF363C76D9234E01C9077401C57C89EEB |texte= Cross-learning in analytic word recognition without segmentation }}
This area was generated with Dilib version V0.6.33. |