A Mask-based enhancement method for historical documents
Identifieur interne : 000580 ( Main/Exploration ); précédent : 000579; suivant : 000581A Mask-based enhancement method for historical documents
Auteurs : Elisa H. Barney Smith [États-Unis] ; Jérôme Darbon [France] ; Laurence Likforman-Sulem [France]Source :
- Proceedings of SPIE, the International Society for Optical Engineering [ 0277-786X ] ; 2011.
Descripteurs français
- Pascal (Inist)
- Wicri :
- topic : Télévision.
English descriptors
- KwdEn :
Abstract
This paper proposes a novel method for document enhancement. The method is based on the combination of two state-of-the-art filters through the construction of a mask. The mask is applied to a TV (Total Variation) -regularized image where background noise has been reduced. The masked image is then filtered by NLmeans (Non Local Means) which reduces the noise in the text areas located by the mask. The document images to be enhanced are real historical documents from several periods which include several defects in their background. These defects result from scanning, paper aging and bleed-through. We observe the improvement of this enhancement method through OCR accuracy.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000131
- to stream PascalFrancis, to step Curation: 000642
- to stream PascalFrancis, to step Checkpoint: 000134
- to stream Main, to step Merge: 000586
- to stream Main, to step Curation: 000580
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">A Mask-based enhancement method for historical documents</title>
<author><name sortKey="Barney Smith, Elisa H" sort="Barney Smith, Elisa H" uniqKey="Barney Smith E" first="Elisa H." last="Barney Smith">Elisa H. Barney Smith</name>
<affiliation wicri:level="2"><inist:fA14 i1="01"><s1>Boise State University</s1>
<s2>Boise, Idaho</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><region type="state">Idaho</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Darbon, Jerome" sort="Darbon, Jerome" uniqKey="Darbon J" first="Jérôme" last="Darbon">Jérôme Darbon</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>CMLA, ENS Cachan, CNRS, PRES UniverSud</s1>
<s3>FRA</s3>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>France</country>
<wicri:noRegion>PRES UniverSud</wicri:noRegion>
<wicri:noRegion>CMLA, ENS Cachan, CNRS, PRES UniverSud</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Likforman Sulem, Laurence" sort="Likforman Sulem, Laurence" uniqKey="Likforman Sulem L" first="Laurence" last="Likforman-Sulem">Laurence Likforman-Sulem</name>
<affiliation wicri:level="1"><inist:fA14 i1="03"><s1>Telecom ParisTech</s1>
<s2>Paris</s2>
<s3>FRA</s3>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><settlement type="city">Paris</settlement>
</placeName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">11-0279166</idno>
<date when="2011">2011</date>
<idno type="stanalyst">PASCAL 11-0279166 INIST</idno>
<idno type="RBID">Pascal:11-0279166</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000131</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000642</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000134</idno>
<idno type="wicri:doubleKey">0277-786X:2011:Barney Smith E:a:mask:based</idno>
<idno type="wicri:Area/Main/Merge">000586</idno>
<idno type="wicri:Area/Main/Curation">000580</idno>
<idno type="wicri:Area/Main/Exploration">000580</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">A Mask-based enhancement method for historical documents</title>
<author><name sortKey="Barney Smith, Elisa H" sort="Barney Smith, Elisa H" uniqKey="Barney Smith E" first="Elisa H." last="Barney Smith">Elisa H. Barney Smith</name>
<affiliation wicri:level="2"><inist:fA14 i1="01"><s1>Boise State University</s1>
<s2>Boise, Idaho</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><region type="state">Idaho</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Darbon, Jerome" sort="Darbon, Jerome" uniqKey="Darbon J" first="Jérôme" last="Darbon">Jérôme Darbon</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>CMLA, ENS Cachan, CNRS, PRES UniverSud</s1>
<s3>FRA</s3>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>France</country>
<wicri:noRegion>PRES UniverSud</wicri:noRegion>
<wicri:noRegion>CMLA, ENS Cachan, CNRS, PRES UniverSud</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Likforman Sulem, Laurence" sort="Likforman Sulem, Laurence" uniqKey="Likforman Sulem L" first="Laurence" last="Likforman-Sulem">Laurence Likforman-Sulem</name>
<affiliation wicri:level="1"><inist:fA14 i1="03"><s1>Telecom ParisTech</s1>
<s2>Paris</s2>
<s3>FRA</s3>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><settlement type="city">Paris</settlement>
</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>Accuracy</term>
<term>Aging</term>
<term>Background</term>
<term>Background noise</term>
<term>Document image processing</term>
<term>Imagery</term>
<term>Noise reduction</term>
<term>Non-local means method</term>
<term>Optical character recognition</term>
<term>State of the art</term>
<term>Television</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Imagerie</term>
<term>Vieillissement</term>
<term>Etat actuel</term>
<term>Télévision</term>
<term>Bruit fond</term>
<term>Réduction bruit</term>
<term>Traitement image document</term>
<term>Reconnaissance optique caractère</term>
<term>Précision</term>
<term>0130C</term>
<term>4230</term>
<term>Méthode des moyennes non-locales</term>
<term>Arrière plan</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Télévision</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">This paper proposes a novel method for document enhancement. The method is based on the combination of two state-of-the-art filters through the construction of a mask. The mask is applied to a TV (Total Variation) -regularized image where background noise has been reduced. The masked image is then filtered by NLmeans (Non Local Means) which reduces the noise in the text areas located by the mask. The document images to be enhanced are real historical documents from several periods which include several defects in their background. These defects result from scanning, paper aging and bleed-through. We observe the improvement of this enhancement method through OCR accuracy.</div>
</front>
</TEI>
<affiliations><list><country><li>France</li>
<li>États-Unis</li>
</country>
<region><li>Idaho</li>
</region>
<settlement><li>Paris</li>
</settlement>
</list>
<tree><country name="États-Unis"><region name="Idaho"><name sortKey="Barney Smith, Elisa H" sort="Barney Smith, Elisa H" uniqKey="Barney Smith E" first="Elisa H." last="Barney Smith">Elisa H. Barney Smith</name>
</region>
</country>
<country name="France"><noRegion><name sortKey="Darbon, Jerome" sort="Darbon, Jerome" uniqKey="Darbon J" first="Jérôme" last="Darbon">Jérôme Darbon</name>
</noRegion>
<name sortKey="Likforman Sulem, Laurence" sort="Likforman Sulem, Laurence" uniqKey="Likforman Sulem L" first="Laurence" last="Likforman-Sulem">Laurence Likforman-Sulem</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 000580 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000580 | 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:11-0279166 |texte= A Mask-based enhancement method for historical documents }}
This area was generated with Dilib version V0.6.32. |