Hybrid OCR Combination for Ancient Documents
Identifieur interne : 000206 ( France/Analysis ); précédent : 000205; suivant : 000207Hybrid OCR Combination for Ancient Documents
Auteurs : Hubert Cecotti [France] ; Abdel Belaïd [France]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2005.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
Abstract: Commercial Optical Character Recognition (OCR) have at lot improved in the last few years. Their outstanding ability to process different kinds of documents is their main quality. However, their generality can also be an issue, as they cannot recognize perfectly documents far from the average present-day documents. We propose in this paper a system combining several OCRs and a specialized ICR (Intelligent Character Recognition) based on a convolutional neural network to complement them. Instead of just performing several OCRs in parallel and applying a fusing rule on the results, a specialized neural network with an adaptive topology is added to complement the OCRs, in function of the OCRs errors. This system has been tested on ancient documents containing old characters and old fonts not used in contemporary documents. The OCRs combination increases the recognition of about 3% whereas the ICR improves the recognition of rejected characters of more than 5%.
Url:
DOI: 10.1007/11551188_71
Affiliations:
- France
- Alsace-Champagne-Ardenne-Lorraine, Région Lorraine
- Nancy, Vandœuvre-lès-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: 000395
- to stream Istex, to step Curation: 000389
- to stream Istex, to step Checkpoint: 000C03
- to stream Main, to step Merge: 001330
- to stream PascalFrancis, to step Corpus: 000449
- to stream PascalFrancis, to step Curation: 000339
- to stream PascalFrancis, to step Checkpoint: 000403
- to stream Main, to step Merge: 001433
- to stream Main, to step Curation: 001294
- to stream Main, to step Exploration: 001294
- to stream France, to step Extraction: 000206
Links to Exploration step
ISTEX:FFEAD1F3CDBEF35E2AC2B68BB2C35789522DCB30Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Hybrid OCR Combination for Ancient Documents</title><author><name sortKey="Cecotti, Hubert" sort="Cecotti, Hubert" uniqKey="Cecotti H" first="Hubert" last="Cecotti">Hubert Cecotti</name></author><author><name sortKey="Belaid, Abdel" sort="Belaid, Abdel" uniqKey="Belaid A" first="Abdel" 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></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:FFEAD1F3CDBEF35E2AC2B68BB2C35789522DCB30</idno><date when="2005" year="2005">2005</date><idno type="doi">10.1007/11551188_71</idno><idno type="url">https://api.istex.fr/document/FFEAD1F3CDBEF35E2AC2B68BB2C35789522DCB30/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000395</idno><idno type="wicri:Area/Istex/Curation">000389</idno><idno type="wicri:Area/Istex/Checkpoint">000C03</idno><idno type="wicri:doubleKey">0302-9743:2005:Cecotti H:hybrid:ocr:combination</idno><idno type="wicri:Area/Main/Merge">001330</idno><idno type="wicri:source">INIST</idno><idno type="RBID">Pascal:05-0391622</idno><idno type="wicri:Area/PascalFrancis/Corpus">000449</idno><idno type="wicri:Area/PascalFrancis/Curation">000339</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000403</idno><idno type="wicri:doubleKey">0302-9743:2005:Cecotti H:hybrid:ocr:combination</idno><idno type="wicri:Area/Main/Merge">001433</idno><idno type="wicri:Area/Main/Curation">001294</idno><idno type="wicri:Area/Main/Exploration">001294</idno><idno type="wicri:Area/France/Extraction">000206</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Hybrid OCR Combination for Ancient Documents</title><author><name sortKey="Cecotti, Hubert" sort="Cecotti, Hubert" uniqKey="Cecotti H" first="Hubert" last="Cecotti">Hubert Cecotti</name><affiliation wicri:level="1"><country xml:lang="fr">France</country><wicri:regionArea>READ Group, LORIA/CNRS, Campus Scientifique, BP 239, 54506 cedex, Vandoeuvre-les-Nancy</wicri:regionArea><placeName><settlement type="city">Vandœuvre-lès-Nancy</settlement><settlement type="city" wicri:auto="agglo">Nancy</settlement></placeName></affiliation></author><author><name sortKey="Belaid, Abdel" sort="Belaid, Abdel" uniqKey="Belaid A" first="Abdel" last="Belaïd">Abdel Belaïd</name><affiliation wicri:level="1"><country xml:lang="fr">France</country><wicri:regionArea>READ Group, LORIA/CNRS, Campus Scientifique, BP 239, 54506 cedex, Vandoeuvre-les-Nancy</wicri:regionArea><placeName><settlement type="city">Vandœuvre-lès-Nancy</settlement><settlement type="city" wicri:auto="agglo">Nancy</settlement></placeName><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></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>2005</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">FFEAD1F3CDBEF35E2AC2B68BB2C35789522DCB30</idno><idno type="DOI">10.1007/11551188_71</idno><idno type="ChapterID">71</idno><idno type="ChapterID">Chap71</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0302-9743</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Adaptive method</term><term>Character recognition</term><term>Data mining</term><term>Error function</term><term>Network topology</term><term>Neural network</term><term>Optical character recognition</term><term>Pattern recognition</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Fonction erreur</term><term>Fouille donnée</term><term>Méthode adaptative</term><term>Reconnaissance caractère</term><term>Reconnaissance forme</term><term>Reconnaissance optique caractère</term><term>Réseau neuronal</term><term>Topologie circuit</term></keywords></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: Commercial Optical Character Recognition (OCR) have at lot improved in the last few years. Their outstanding ability to process different kinds of documents is their main quality. However, their generality can also be an issue, as they cannot recognize perfectly documents far from the average present-day documents. We propose in this paper a system combining several OCRs and a specialized ICR (Intelligent Character Recognition) based on a convolutional neural network to complement them. Instead of just performing several OCRs in parallel and applying a fusing rule on the results, a specialized neural network with an adaptive topology is added to complement the OCRs, in function of the OCRs errors. This system has been tested on ancient documents containing old characters and old fonts not used in contemporary documents. The OCRs combination increases the recognition of about 3% whereas the ICR improves the recognition of rejected characters of more than 5%.</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><li>Vandœuvre-lès-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><country name="France"><noRegion><name sortKey="Cecotti, Hubert" sort="Cecotti, Hubert" uniqKey="Cecotti H" first="Hubert" last="Cecotti">Hubert Cecotti</name></noRegion><name sortKey="Belaid, Abdel" sort="Belaid, Abdel" uniqKey="Belaid A" first="Abdel" last="Belaïd">Abdel Belaïd</name></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 000206 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/France/Analysis/biblio.hfd -nk 000206 | 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= ISTEX:FFEAD1F3CDBEF35E2AC2B68BB2C35789522DCB30
|texte= Hybrid OCR Combination for Ancient Documents
}}
| This area was generated with Dilib version V0.6.32. |  |