Application of Hidden Markov Models to Multifont Next Recognition
Identifieur interne : 00D844 ( Main/Exploration ); précédent : 00D843; suivant : 00D845Application of Hidden Markov Models to Multifont Next Recognition
Auteurs : J.-C. Anigbogu ; Abdel Belaïd [France]Source :
English descriptors
- KwdEn :
Abstract
This paper describes a multifont recognition system that uses Hidden Markov Models. This system works in two phases. In the first phase, it detects the predominant font in the current paragraph and then uses the Modified Viterbi Algorithm to recognize the characters. The choice of the predominant font and the examination of certain features permit a further reduction of the number of models to be traited. The second phase deals with the grouping of characters into words and verification using an application dictionary or digrams. Character recognition results on ten fonts range between 96========percnt; and 99.82========percnt; depending on the font.
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 Crin, to step Corpus: 000B57
- to stream Crin, to step Curation: 000B57
- to stream Crin, to step Checkpoint: 003921
- to stream Main, to step Merge: 00E122
- to stream Main, to step Curation: 00D844
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="481">Application of Hidden Markov Models to Multifont Next Recognition</title>
</titleStmt>
<publicationStmt><idno type="RBID">CRIN:anigbogu91b</idno>
<date when="1991" year="1991">1991</date>
<idno type="wicri:Area/Crin/Corpus">000B57</idno>
<idno type="wicri:Area/Crin/Curation">000B57</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">000B57</idno>
<idno type="wicri:Area/Crin/Checkpoint">003921</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">003921</idno>
<idno type="wicri:Area/Main/Merge">00E122</idno>
<idno type="wicri:Area/Main/Curation">00D844</idno>
<idno type="wicri:Area/Main/Exploration">00D844</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Application of Hidden Markov Models to Multifont Next Recognition</title>
<author><name sortKey="Anigbogu, J C" sort="Anigbogu, J C" uniqKey="Anigbogu J" first="J.-C." last="Anigbogu">J.-C. Anigbogu</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>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Hidden Markov Models</term>
<term>Viterbi algorithm</term>
<term>font determination</term>
<term>multifont character recognition</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en" wicri:score="1930">This paper describes a multifont recognition system that uses Hidden Markov Models. This system works in two phases. In the first phase, it detects the predominant font in the current paragraph and then uses the Modified Viterbi Algorithm to recognize the characters. The choice of the predominant font and the examination of certain features permit a further reduction of the number of models to be traited. The second phase deals with the grouping of characters into words and verification using an application dictionary or digrams. Character recognition results on ten fonts range between 96========percnt; and 99.82========percnt; depending on the font.</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="Anigbogu, J C" sort="Anigbogu, J C" uniqKey="Anigbogu J" first="J.-C." last="Anigbogu">J.-C. Anigbogu</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 00D844 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 00D844 | 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= CRIN:anigbogu91b |texte= Application of Hidden Markov Models to Multifont Next Recognition }}
![]() | This area was generated with Dilib version V0.6.33. | ![]() |