Unsupervised Method to Generate Page Templates
Identifieur interne : 000537 ( Main/Exploration ); précédent : 000536; suivant : 000538Unsupervised Method to Generate Page Templates
Auteurs : Herve DejeanSource :
- Proceedings of SPIE, the International Society for Optical Engineering [ 0277-786X ] ; 2011.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
In this paper, we propose a method for automatically inferring the different page templates used to layout the document content. The first step of the method consists in performing a logical analysis of the document. Depending of the coverage of this step, a given number of document elements will be labeled. Then geometric relations are computed between these labeled elements, and page templates candidates are generated using frequent related elements. A fuzzy matching operation allows for selecting the most frequent and relevant page templates for a given document. Such page templates can be used to correct errors produced during the different previous steps of the document analysis: zoning, OCR, and logical analysis. Evaluation has been performed using the INEX book track collection.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000133
- to stream PascalFrancis, to step Curation: 000640
- to stream PascalFrancis, to step Checkpoint: 000091
- to stream Main, to step Merge: 000543
- to stream Main, to step Curation: 000537
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Unsupervised Method to Generate Page Templates</title>
<author><name sortKey="Dejean, Herve" sort="Dejean, Herve" uniqKey="Dejean H" first="Herve" last="Dejean">Herve Dejean</name>
<affiliation><inist:fA14 i1="01"><s1>Xerox Research Centre</s1>
<s3>EUR</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
<wicri:noCountry>EUR</wicri:noCountry>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">11-0279160</idno>
<date when="2011">2011</date>
<idno type="stanalyst">PASCAL 11-0279160 INIST</idno>
<idno type="RBID">Pascal:11-0279160</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000133</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000640</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000091</idno>
<idno type="wicri:doubleKey">0277-786X:2011:Dejean H:unsupervised:method:to</idno>
<idno type="wicri:Area/Main/Merge">000543</idno>
<idno type="wicri:Area/Main/Curation">000537</idno>
<idno type="wicri:Area/Main/Exploration">000537</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Unsupervised Method to Generate Page Templates</title>
<author><name sortKey="Dejean, Herve" sort="Dejean, Herve" uniqKey="Dejean H" first="Herve" last="Dejean">Herve Dejean</name>
<affiliation><inist:fA14 i1="01"><s1>Xerox Research Centre</s1>
<s3>EUR</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
<wicri:noCountry>EUR</wicri:noCountry>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Proceedings of SPIE, the International Society for Optical Engineering</title>
<title level="j" type="abbreviated">Proc. SPIE Int. Soc. Opt. Eng.</title>
<idno type="ISSN">0277-786X</idno>
<imprint><date when="2011">2011</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">Proceedings of SPIE, the International Society for Optical Engineering</title>
<title level="j" type="abbreviated">Proc. SPIE Int. Soc. Opt. Eng.</title>
<idno type="ISSN">0277-786X</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Coverage</term>
<term>Document analysis</term>
<term>Error correction</term>
<term>Imagery</term>
<term>Optical character recognition</term>
<term>Target tracking</term>
<term>Unsupervised classification</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Imagerie</term>
<term>Classification non supervisée</term>
<term>Couverture</term>
<term>Correction erreur</term>
<term>Analyse documentaire</term>
<term>Reconnaissance optique caractère</term>
<term>Poursuite cible</term>
<term>0130C</term>
<term>4230</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">In this paper, we propose a method for automatically inferring the different page templates used to layout the document content. The first step of the method consists in performing a logical analysis of the document. Depending of the coverage of this step, a given number of document elements will be labeled. Then geometric relations are computed between these labeled elements, and page templates candidates are generated using frequent related elements. A fuzzy matching operation allows for selecting the most frequent and relevant page templates for a given document. Such page templates can be used to correct errors produced during the different previous steps of the document analysis: zoning, OCR, and logical analysis. Evaluation has been performed using the INEX book track collection.</div>
</front>
</TEI>
<affiliations><list></list>
<tree><noCountry><name sortKey="Dejean, Herve" sort="Dejean, Herve" uniqKey="Dejean H" first="Herve" last="Dejean">Herve Dejean</name>
</noCountry>
</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 000537 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000537 | 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:11-0279160 |texte= Unsupervised Method to Generate Page Templates }}
This area was generated with Dilib version V0.6.32. |