Serveur d'exploration sur l'OCR

Attention, ce site est en cours de développement !
Attention, site généré par des moyens informatiques à partir de corpus bruts.
Les informations ne sont donc pas validées.

Ancient documents bleed-through evaluation and its application for predicting OCR error rates

Identifieur interne : 000575 ( Main/Exploration ); précédent : 000574; suivant : 000576

Ancient documents bleed-through evaluation and its application for predicting OCR error rates

Auteurs : V. Rabeux [France] ; N. Journet [France] ; J. P. Domenger [France]

Source :

RBID : Pascal:11-0279183

Descripteurs français

English descriptors

Abstract

This article presents a way to evaluate the bleed-through defect on very old document images. We design measures to quantify and evaluate the verso ink bleeding through the paper onto the recto side. Measuring the bleed-through defect alows us to perform statistical analysis that are able to predict the feasibility of different post-scan tasks. In this article we choose to illustrate our measures by creating two OCR error rate predicting models based bleed-through evaluation. Two models are proposed, one for Abbyy FineReader * which is a very power-full commercial OCR and OCRopus † which is sponsored by Google. Both prediction models appears to be very accurate when calculating various statistic indicators.


Affiliations:


Links toward previous steps (curation, corpus...)


Le document en format XML

<record>
<TEI>
<teiHeader>
<fileDesc>
<titleStmt>
<title xml:lang="en" level="a">Ancient documents bleed-through evaluation and its application for predicting OCR error rates</title>
<author>
<name sortKey="Rabeux, V" sort="Rabeux, V" uniqKey="Rabeux V" first="V." last="Rabeux">V. Rabeux</name>
<affiliation wicri:level="4">
<inist:fA14 i1="01">
<s1>LaBRI, Universite de Bordeaux, 351, cours de la Liberation</s1>
<s2>Talence</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName>
<settlement type="city">Talence</settlement>
<settlement type="city" wicri:auto="agglo">Bordeaux</settlement>
</placeName>
<orgName type="university">Université de Bordeaux</orgName>
<placeName>
<settlement type="city">Bordeaux</settlement>
<region type="region" nuts="2">Aquitaine</region>
</placeName>
</affiliation>
</author>
<author>
<name sortKey="Journet, N" sort="Journet, N" uniqKey="Journet N" first="N." last="Journet">N. Journet</name>
<affiliation wicri:level="4">
<inist:fA14 i1="01">
<s1>LaBRI, Universite de Bordeaux, 351, cours de la Liberation</s1>
<s2>Talence</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName>
<settlement type="city">Talence</settlement>
<settlement type="city" wicri:auto="agglo">Bordeaux</settlement>
</placeName>
<orgName type="university">Université de Bordeaux</orgName>
<placeName>
<settlement type="city">Bordeaux</settlement>
<region type="region" nuts="2">Aquitaine</region>
</placeName>
</affiliation>
</author>
<author>
<name sortKey="Domenger, J P" sort="Domenger, J P" uniqKey="Domenger J" first="J. P" last="Domenger">J. P. Domenger</name>
<affiliation wicri:level="4">
<inist:fA14 i1="01">
<s1>LaBRI, Universite de Bordeaux, 351, cours de la Liberation</s1>
<s2>Talence</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName>
<settlement type="city">Talence</settlement>
<settlement type="city" wicri:auto="agglo">Bordeaux</settlement>
</placeName>
<orgName type="university">Université de Bordeaux</orgName>
<placeName>
<settlement type="city">Bordeaux</settlement>
<region type="region" nuts="2">Aquitaine</region>
</placeName>
</affiliation>
</author>
</titleStmt>
<publicationStmt>
<idno type="wicri:source">INIST</idno>
<idno type="inist">11-0279183</idno>
<date when="2011">2011</date>
<idno type="stanalyst">PASCAL 11-0279183 INIST</idno>
<idno type="RBID">Pascal:11-0279183</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000130</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000643</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000129</idno>
<idno type="wicri:doubleKey">0277-786X:2011:Rabeux V:ancient:documents:bleed</idno>
<idno type="wicri:Area/Main/Merge">000581</idno>
<idno type="wicri:Area/Main/Curation">000575</idno>
<idno type="wicri:Area/Main/Exploration">000575</idno>
</publicationStmt>
<sourceDesc>
<biblStruct>
<analytic>
<title xml:lang="en" level="a">Ancient documents bleed-through evaluation and its application for predicting OCR error rates</title>
<author>
<name sortKey="Rabeux, V" sort="Rabeux, V" uniqKey="Rabeux V" first="V." last="Rabeux">V. Rabeux</name>
<affiliation wicri:level="4">
<inist:fA14 i1="01">
<s1>LaBRI, Universite de Bordeaux, 351, cours de la Liberation</s1>
<s2>Talence</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName>
<settlement type="city">Talence</settlement>
<settlement type="city" wicri:auto="agglo">Bordeaux</settlement>
</placeName>
<orgName type="university">Université de Bordeaux</orgName>
<placeName>
<settlement type="city">Bordeaux</settlement>
<region type="region" nuts="2">Aquitaine</region>
</placeName>
</affiliation>
</author>
<author>
<name sortKey="Journet, N" sort="Journet, N" uniqKey="Journet N" first="N." last="Journet">N. Journet</name>
<affiliation wicri:level="4">
<inist:fA14 i1="01">
<s1>LaBRI, Universite de Bordeaux, 351, cours de la Liberation</s1>
<s2>Talence</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName>
<settlement type="city">Talence</settlement>
<settlement type="city" wicri:auto="agglo">Bordeaux</settlement>
</placeName>
<orgName type="university">Université de Bordeaux</orgName>
<placeName>
<settlement type="city">Bordeaux</settlement>
<region type="region" nuts="2">Aquitaine</region>
</placeName>
</affiliation>
</author>
<author>
<name sortKey="Domenger, J P" sort="Domenger, J P" uniqKey="Domenger J" first="J. P" last="Domenger">J. P. Domenger</name>
<affiliation wicri:level="4">
<inist:fA14 i1="01">
<s1>LaBRI, Universite de Bordeaux, 351, cours de la Liberation</s1>
<s2>Talence</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName>
<settlement type="city">Talence</settlement>
<settlement type="city" wicri:auto="agglo">Bordeaux</settlement>
</placeName>
<orgName type="university">Université de Bordeaux</orgName>
<placeName>
<settlement type="city">Bordeaux</settlement>
<region type="region" nuts="2">Aquitaine</region>
</placeName>
</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>Document image processing</term>
<term>Error rate</term>
<term>Feasibility</term>
<term>Imagery</term>
<term>Inks</term>
<term>Old document</term>
<term>Optical character recognition</term>
<term>Statistical method</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr">
<term>Imagerie</term>
<term>Encre</term>
<term>Reconnaissance optique caractère</term>
<term>Taux erreur</term>
<term>Document ancien</term>
<term>Traitement image document</term>
<term>Méthode statistique</term>
<term>Faisabilité</term>
<term>0130C</term>
<term>4230</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr">
<term>Méthode statistique</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front>
<div type="abstract" xml:lang="en">This article presents a way to evaluate the bleed-through defect on very old document images. We design measures to quantify and evaluate the verso ink bleeding through the paper onto the recto side. Measuring the bleed-through defect alows us to perform statistical analysis that are able to predict the feasibility of different post-scan tasks. In this article we choose to illustrate our measures by creating two OCR error rate predicting models based bleed-through evaluation. Two models are proposed, one for Abbyy FineReader
<sup>*</sup>
which is a very power-full commercial OCR and OCRopus † which is sponsored by Google. Both prediction models appears to be very accurate when calculating various statistic indicators.</div>
</front>
</TEI>
<affiliations>
<list>
<country>
<li>France</li>
</country>
<region>
<li>Aquitaine</li>
</region>
<settlement>
<li>Bordeaux</li>
<li>Talence</li>
</settlement>
<orgName>
<li>Université de Bordeaux</li>
</orgName>
</list>
<tree>
<country name="France">
<noRegion>
<name sortKey="Rabeux, V" sort="Rabeux, V" uniqKey="Rabeux V" first="V." last="Rabeux">V. Rabeux</name>
</noRegion>
<name sortKey="Domenger, J P" sort="Domenger, J P" uniqKey="Domenger J" first="J. P" last="Domenger">J. P. Domenger</name>
<name sortKey="Journet, N" sort="Journet, N" uniqKey="Journet N" first="N." last="Journet">N. Journet</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 000575 | SxmlIndent | more

Ou

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000575 | 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:11-0279183
   |texte=   Ancient documents bleed-through evaluation and its application for predicting OCR error rates
}}

Wicri

This area was generated with Dilib version V0.6.32.
Data generation: Sat Nov 11 16:53:45 2017. Site generation: Mon Mar 11 23:15:16 2024