Cross-learning in analytic word recognition without segmentation
Identifieur interne : 008818 ( Main/Exploration ); précédent : 008817; suivant : 008819Cross-learning in analytic word recognition without segmentation
Auteurs : C. Choisy ; Abdel Belaïd [France]Source :
- International Journal on Document Analysis and Recognition [ 1433-2833 ] ; 2002-07-01.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
- mix :
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
Affiliations:
- France
- Grand Est, Lorraine (région)
- Nancy
- Centre national de la recherche scientifique, Institut national de recherche en informatique et en automatique, Laboratoire lorrain de recherche en informatique et ses applications, Université de Lorraine
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 001393
- to stream Istex, to step Curation: 001376
- to stream Istex, to step Checkpoint: 001C54
- to stream Main, to step Merge: 008C74
- to stream Hal, to step Corpus: 001997
- to stream Hal, to step Curation: 001997
- to stream Hal, to step Checkpoint: 005A13
- to stream Main, to step Merge: 009085
- to stream PascalFrancis, to step Corpus: 000858
- to stream PascalFrancis, to step Curation: 000194
- to stream PascalFrancis, to step Checkpoint: 000815
- to stream Main, to step Merge: 008E00
- to stream Main, to step Curation: 008818
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>
</author>
<author><name sortKey="Belaid, A" sort="Belaid, A" uniqKey="Belaid A" first="A." last="Belaïd">Abdel Belaïd</name>
<affiliation><country>France</country>
<placeName><settlement type="city">Nancy</settlement>
<region type="region" nuts="2">Grand Est</region>
<region type="region" nuts="2">Lorraine (région)</region>
</placeName>
<orgName type="laboratoire" n="5">Laboratoire lorrain de recherche en informatique et ses applications</orgName>
<orgName type="university">Université de Lorraine</orgName>
<orgName type="institution">Centre national de la recherche scientifique</orgName>
<orgName type="institution">Institut national de recherche en informatique et en automatique</orgName>
</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>
<idno type="wicri:Area/Istex/Checkpoint">001C54</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">001C54</idno>
<idno type="wicri:doubleKey">1433-2833:2002:Choisy C:cross:learning:in</idno>
<idno type="wicri:Area/Main/Merge">008C74</idno>
<idno type="wicri:source">HAL</idno>
<idno type="RBID">Hal:inria-00100851</idno>
<idno type="url">https://hal.inria.fr/inria-00100851</idno>
<idno type="wicri:Area/Hal/Corpus">001997</idno>
<idno type="wicri:Area/Hal/Curation">001997</idno>
<idno type="wicri:Area/Hal/Checkpoint">005A13</idno>
<idno type="wicri:explorRef" wicri:stream="Hal" wicri:step="Checkpoint">005A13</idno>
<idno type="wicri:doubleKey">1433-2833:2002:Choisy C:cross:learning:in</idno>
<idno type="wicri:Area/Main/Merge">009085</idno>
<idno type="wicri:source">INIST</idno>
<idno type="RBID">Pascal:02-0499049</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000858</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000194</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000815</idno>
<idno type="wicri:explorRef" wicri:stream="PascalFrancis" wicri:step="Checkpoint">000815</idno>
<idno type="wicri:doubleKey">1433-2833:2002:Choisy C:cross:learning:in</idno>
<idno type="wicri:Area/Main/Merge">008E00</idno>
<idno type="wicri:Area/Main/Curation">008818</idno>
<idno type="wicri:Area/Main/Exploration">008818</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><wicri:noCountry code="subField">FR</wicri:noCountry>
</affiliation>
</author>
<author><name sortKey="Belaid, A" sort="Belaid, A" uniqKey="Belaid A" first="A." last="Belaïd">Abdel Belaïd</name>
<affiliation><wicri:noCountry code="subField">FR</wicri:noCountry>
<country>France</country>
<placeName><settlement type="city">Nancy</settlement>
<region type="region" nuts="2">Grand Est</region>
<region type="region" nuts="2">Lorraine (région)</region>
</placeName>
<orgName type="laboratoire" n="5">Laboratoire lorrain de recherche en informatique et ses applications</orgName>
<orgName type="university">Université de Lorraine</orgName>
<orgName type="institution">Centre national de la recherche scientifique</orgName>
<orgName type="institution">Institut national de recherche en informatique et en automatique</orgName>
</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>Causality</term>
<term>Character recognition</term>
<term>Hidden Markov model</term>
<term>Image processing</term>
<term>Key words:hmm, nshp-hmm, Cross-learning, Meta-models, Baum-Welch Algorithm</term>
<term>Letter</term>
<term>Markov process</term>
<term>Metamodel</term>
<term>Segmentation</term>
<term>Word</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Causalité</term>
<term>Lettre alphabet</term>
<term>Modèle Markov caché</term>
<term>Mot</term>
<term>Métamodèle</term>
<term>Processus Markov</term>
<term>Reconnaissance caractère</term>
<term>Segmentation</term>
<term>Traitement image</term>
</keywords>
<keywords scheme="mix" xml:lang="en"><term>baum algorithm</term>
<term>cross-learning</term>
<term>hmm</term>
<term>meta-models</term>
<term>nshp</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>
<affiliations><list><country><li>France</li>
</country>
<region><li>Grand Est</li>
<li>Lorraine (région)</li>
</region>
<settlement><li>Nancy</li>
</settlement>
<orgName><li>Centre national de la recherche scientifique</li>
<li>Institut national de recherche en informatique et en automatique</li>
<li>Laboratoire lorrain de recherche en informatique et ses applications</li>
<li>Université de Lorraine</li>
</orgName>
</list>
<tree><noCountry><name sortKey="Choisy, C" sort="Choisy, C" uniqKey="Choisy C" first="C." last="Choisy">C. Choisy</name>
</noCountry>
<country name="France"><region name="Grand Est"><name sortKey="Belaid, A" sort="Belaid, A" uniqKey="Belaid A" first="A." last="Belaïd">Abdel Belaïd</name>
</region>
</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 008818 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 008818 | 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= ISTEX:55280B7BF363C76D9234E01C9077401C57C89EEB |texte= Cross-learning in analytic word recognition without segmentation }}
This area was generated with Dilib version V0.6.33. |