Text Recognition Using Stochastic Models
Identifieur interne : 000380 ( France/Analysis ); précédent : 000379; suivant : 000381Text Recognition Using Stochastic Models
Auteurs : Abdel Belaïd [France] ; J.-C. AnigboguSource :
English descriptors
Abstract
This paper describes a character recognition system that uses first order Hidden Markov models to treat multifont printed text. The text is first segmented into characters from where features are deduced and quantized. The Modified Viterbi Algorithm is the recognition method chosen. Depending on choice, the system outputs strings of characters, supposedly words, or the string is first matched against a dictionary or the string is passed through a Viterbi net with the output being the recognized word. In tests with deterministic decision trees, the performance is promising in multifont optical character recognition.
Affiliations:
- France
- Alsace-Champagne-Ardenne-Lorraine, Région Lorraine
- 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: 000006
- to stream Crin, to step Curation: 000006
- to stream Crin, to step Checkpoint: 000007
- to stream Main, to step Merge: 003595
- to stream Main, to step Curation: 003408
- to stream Main, to step Exploration: 003408
- to stream France, to step Extraction: 000380
Links to Exploration step
CRIN:belaid91bLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="288">Text Recognition Using Stochastic Models</title>
</titleStmt>
<publicationStmt><idno type="RBID">CRIN:belaid91b</idno>
<date when="1991" year="1991">1991</date>
<idno type="wicri:Area/Crin/Corpus">000006</idno>
<idno type="wicri:Area/Crin/Curation">000006</idno>
<idno type="wicri:Area/Crin/Checkpoint">000007</idno>
<idno type="wicri:Area/Main/Merge">003595</idno>
<idno type="wicri:Area/Main/Curation">003408</idno>
<idno type="wicri:Area/Main/Exploration">003408</idno>
<idno type="wicri:Area/France/Extraction">000380</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Text Recognition Using Stochastic Models</title>
<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">Alsace-Champagne-Ardenne-Lorraine</region>
<region type="region" nuts="2">Région Lorraine</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>
<author><name sortKey="Anigbogu, J C" sort="Anigbogu, J C" uniqKey="Anigbogu J" first="J.-C." last="Anigbogu">J.-C. Anigbogu</name>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Baum-Welch algorithm</term>
<term>Markov models</term>
<term>OCR</term>
<term>Viterbi algorithm</term>
<term>character recognition</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en" wicri:score="1461">This paper describes a character recognition system that uses first order Hidden Markov models to treat multifont printed text. The text is first segmented into characters from where features are deduced and quantized. The Modified Viterbi Algorithm is the recognition method chosen. Depending on choice, the system outputs strings of characters, supposedly words, or the string is first matched against a dictionary or the string is passed through a Viterbi net with the output being the recognized word. In tests with deterministic decision trees, the performance is promising in multifont optical character recognition.</div>
</front>
</TEI>
<affiliations><list><country><li>France</li>
</country>
<region><li>Alsace-Champagne-Ardenne-Lorraine</li>
<li>Région Lorraine</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="Alsace-Champagne-Ardenne-Lorraine"><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/Ticri/CIDE/explor/OcrV1/Data/France/Analysis
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000380 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/France/Analysis/biblio.hfd -nk 000380 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= France |étape= Analysis |type= RBID |clé= CRIN:belaid91b |texte= Text Recognition Using Stochastic Models }}
This area was generated with Dilib version V0.6.32. |