Using topic models for OCR correction
Identifieur interne : 000A63 ( Main/Exploration ); précédent : 000A62; suivant : 000A64Using topic models for OCR correction
Auteurs : Faisal Farooq [États-Unis] ; Anurag Bhardwaj [États-Unis] ; Venugopal Govindaraju [États-Unis]Source :
- International journal on document analysis and recognition : (Print) [ 1433-2833 ] ; 2009.
Descripteurs français
- Pascal (Inist)
- Wicri :
- topic : Base de données.
English descriptors
- KwdEn :
Abstract
Despite several decades of research in document analysis, recognition of unconstrained handwritten documents is still considered a challenging task. Previous research in this area has shown that word recognizers perform adequately on constrained handwritten documents which typically use a restricted vocabulary (lexicon). But in the case of unconstrained handwritten documents, state-of-the-art word recognition accuracy is still below the acceptable limits. The objective of this research is to improve word recognition accuracy on unconstrained handwritten documents by applying a post-processing or OCR correction technique to the word recognition output. In this paper, we present two different methods for this purpose. First, we describe a lexicon reduction-based method by topic categorization of handwritten documents which is used to generate smaller topic-specific lexicons for improving the recognition accuracy. Second, we describe a method which uses topic-specific language models and a maximum-entropy based topic categorization model to refine the recognition output. We present the relative merits of each of these methods and report results on the publicly available IAM database.
Affiliations:
- États-Unis
- Pennsylvanie, État de New York
- Buffalo (New York)
- Université d'État de New York, Université d'État de New York à Buffalo
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000196
- to stream PascalFrancis, to step Curation: 000581
- to stream PascalFrancis, to step Checkpoint: 000178
- to stream Main, to step Merge: 000A72
- to stream Main, to step Curation: 000A63
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Using topic models for OCR correction</title>
<author><name sortKey="Farooq, Faisal" sort="Farooq, Faisal" uniqKey="Farooq F" first="Faisal" last="Farooq">Faisal Farooq</name>
<affiliation wicri:level="2"><inist:fA14 i1="01"><s1>Image and Knowledge Management, Siemens Medical Solutions</s1>
<s2>Malvern, PA</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><region type="state">Pennsylvanie</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Bhardwaj, Anurag" sort="Bhardwaj, Anurag" uniqKey="Bhardwaj A" first="Anurag" last="Bhardwaj">Anurag Bhardwaj</name>
<affiliation wicri:level="4"><inist:fA14 i1="02"><s1>Department of Computer Science and Engineering, University at Buffalo</s1>
<s2>Buffalo, NY</s2>
<s3>USA</s3>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><region type="state">État de New York</region>
<settlement type="city">Buffalo (New York)</settlement>
</placeName>
<orgName type="university">Université d'État de New York à Buffalo</orgName>
</affiliation>
</author>
<author><name sortKey="Govindaraju, Venu" sort="Govindaraju, Venu" uniqKey="Govindaraju V" first="Venu" last="Govindaraju">Venugopal Govindaraju</name>
<affiliation wicri:level="4"><inist:fA14 i1="02"><s1>Department of Computer Science and Engineering, University at Buffalo</s1>
<s2>Buffalo, NY</s2>
<s3>USA</s3>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><region type="state">État de New York</region>
<settlement type="city">Buffalo (New York)</settlement>
</placeName>
<orgName type="university">Université d'État de New York à Buffalo</orgName>
<placeName><settlement type="city">Buffalo (New York)</settlement>
<region type="state">État de New York</region>
</placeName>
<orgName type="university" n="3">Université d'État de New York à Buffalo</orgName>
<orgName type="institution">Université d'État de New York</orgName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">10-0180626</idno>
<date when="2009">2009</date>
<idno type="stanalyst">PASCAL 10-0180626 INIST</idno>
<idno type="RBID">Pascal:10-0180626</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000196</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000581</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000178</idno>
<idno type="wicri:doubleKey">1433-2833:2009:Farooq F:using:topic:models</idno>
<idno type="wicri:Area/Main/Merge">000A72</idno>
<idno type="wicri:Area/Main/Curation">000A63</idno>
<idno type="wicri:Area/Main/Exploration">000A63</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Using topic models for OCR correction</title>
<author><name sortKey="Farooq, Faisal" sort="Farooq, Faisal" uniqKey="Farooq F" first="Faisal" last="Farooq">Faisal Farooq</name>
<affiliation wicri:level="2"><inist:fA14 i1="01"><s1>Image and Knowledge Management, Siemens Medical Solutions</s1>
<s2>Malvern, PA</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><region type="state">Pennsylvanie</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Bhardwaj, Anurag" sort="Bhardwaj, Anurag" uniqKey="Bhardwaj A" first="Anurag" last="Bhardwaj">Anurag Bhardwaj</name>
<affiliation wicri:level="4"><inist:fA14 i1="02"><s1>Department of Computer Science and Engineering, University at Buffalo</s1>
<s2>Buffalo, NY</s2>
<s3>USA</s3>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><region type="state">État de New York</region>
<settlement type="city">Buffalo (New York)</settlement>
</placeName>
<orgName type="university">Université d'État de New York à Buffalo</orgName>
</affiliation>
</author>
<author><name sortKey="Govindaraju, Venu" sort="Govindaraju, Venu" uniqKey="Govindaraju V" first="Venu" last="Govindaraju">Venugopal Govindaraju</name>
<affiliation wicri:level="4"><inist:fA14 i1="02"><s1>Department of Computer Science and Engineering, University at Buffalo</s1>
<s2>Buffalo, NY</s2>
<s3>USA</s3>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><region type="state">État de New York</region>
<settlement type="city">Buffalo (New York)</settlement>
</placeName>
<orgName type="university">Université d'État de New York à Buffalo</orgName>
<placeName><settlement type="city">Buffalo (New York)</settlement>
<region type="state">État de New York</region>
</placeName>
<orgName type="university" n="3">Université d'État de New York à Buffalo</orgName>
<orgName type="institution">Université d'État de New York</orgName>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">International journal on document analysis and recognition : (Print)</title>
<title level="j" type="abbreviated">Int. j. doc. anal. recognit. : (Print)</title>
<idno type="ISSN">1433-2833</idno>
<imprint><date when="2009">2009</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">International journal on document analysis and recognition : (Print)</title>
<title level="j" type="abbreviated">Int. j. doc. anal. recognit. : (Print)</title>
<idno type="ISSN">1433-2833</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Categorization</term>
<term>Character recognition</term>
<term>Database</term>
<term>Document analysis</term>
<term>Document management</term>
<term>Lexicon</term>
<term>Manuscript character</term>
<term>Method of maximum entropy</term>
<term>Modeling</term>
<term>Natural language</term>
<term>Optical character recognition</term>
<term>Pattern recognition</term>
<term>Vocabulary</term>
<term>Word</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Reconnaissance caractère</term>
<term>Reconnaissance optique caractère</term>
<term>Analyse documentaire</term>
<term>Reconnaissance forme</term>
<term>Caractère manuscrit</term>
<term>Mot</term>
<term>Langage naturel</term>
<term>Base de données</term>
<term>Vocabulaire</term>
<term>Lexique</term>
<term>Gestion document</term>
<term>Catégorisation</term>
<term>Modélisation</term>
<term>Méthode entropie maximum</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Base de données</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Despite several decades of research in document analysis, recognition of unconstrained handwritten documents is still considered a challenging task. Previous research in this area has shown that word recognizers perform adequately on constrained handwritten documents which typically use a restricted vocabulary (lexicon). But in the case of unconstrained handwritten documents, state-of-the-art word recognition accuracy is still below the acceptable limits. The objective of this research is to improve word recognition accuracy on unconstrained handwritten documents by applying a post-processing or OCR correction technique to the word recognition output. In this paper, we present two different methods for this purpose. First, we describe a lexicon reduction-based method by topic categorization of handwritten documents which is used to generate smaller topic-specific lexicons for improving the recognition accuracy. Second, we describe a method which uses topic-specific language models and a maximum-entropy based topic categorization model to refine the recognition output. We present the relative merits of each of these methods and report results on the publicly available IAM database.</div>
</front>
</TEI>
<affiliations><list><country><li>États-Unis</li>
</country>
<region><li>Pennsylvanie</li>
<li>État de New York</li>
</region>
<settlement><li>Buffalo (New York)</li>
</settlement>
<orgName><li>Université d'État de New York</li>
<li>Université d'État de New York à Buffalo</li>
</orgName>
</list>
<tree><country name="États-Unis"><region name="Pennsylvanie"><name sortKey="Farooq, Faisal" sort="Farooq, Faisal" uniqKey="Farooq F" first="Faisal" last="Farooq">Faisal Farooq</name>
</region>
<name sortKey="Bhardwaj, Anurag" sort="Bhardwaj, Anurag" uniqKey="Bhardwaj A" first="Anurag" last="Bhardwaj">Anurag Bhardwaj</name>
<name sortKey="Govindaraju, Venu" sort="Govindaraju, Venu" uniqKey="Govindaraju V" first="Venu" last="Govindaraju">Venugopal Govindaraju</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 000A63 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000A63 | 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= Pascal:10-0180626 |texte= Using topic models for OCR correction }}
This area was generated with Dilib version V0.6.32. |