OcrV1, Main, Exploration, bibRecord, 000799

A binarization method with learning-built rules for document images produced by cameras

Identifieur interne : 000799 ( Main/Exploration ); précédent : 000798; suivant : 000800

A binarization method with learning-built rules for document images produced by cameras

Auteurs : Chien-Hsing Chou [Taïwan] ; Wen-Hsiung Lin [Taïwan] ; FU CHANG [Taïwan]

Source :

Pattern recognition [ 0031-3203 ] ; 2010.

RBID : Pascal:10-0118750

Descripteurs français

Pascal (Inist)
- Apprentissage, Traitement image document, Brillance, Méthode statistique, Règle décision, Qualité image, Reconnaissance optique caractère, Evaluation performance, Méthode adaptative, Image binaire, Traitement image, Machine vecteur support, Reconnaissance forme, Classification signal, Classification automatique, Etiquetage multiple.
Wicri :
- topic : Méthode statistique.

English descriptors

KwdEn :
- Adaptive method, Automatic classification, Binary image, Brightness, Decision rule, Document image processing, Image processing, Image quality, Learning, Multilabeling, Optical character recognition, Pattern recognition, Performance evaluation, Signal classification, Statistical method, Support vector machine.

Abstract

In this paper, we propose a novel binarization method for document images produced by cameras. Such images often have varying degrees of brightness and require more careful treatment than merely applying a statistical method to obtain a threshold value. To resolve the problem, the proposed method divides an image into several regions and decides how to binarize each region. The decision rules are derived from a learning process that takes training images as input. Tests on images produced under normal and inadequate illumination conditions show that our method yields better visual quality and better OCR performance than three global binarization methods and four locally adaptive binarization methods.

Affiliations:

Taïwan

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

to stream PascalFrancis, to step Corpus: 000200
to stream PascalFrancis, to step Curation: 000577
to stream PascalFrancis, to step Checkpoint: 000174
to stream Main, to step Merge: 000805
to stream Main, to step Curation: 000799

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">A binarization method with learning-built rules for document images produced by cameras</title>
<author><name sortKey="Chou, Chien Hsing" sort="Chou, Chien Hsing" uniqKey="Chou C" first="Chien-Hsing" last="Chou">Chien-Hsing Chou</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Electrical Engineering, Tamkang University</s1>
<s3>TWN</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
<country>Taïwan</country>
<wicri:noRegion>Department of Electrical Engineering, Tamkang University</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Lin, Wen Hsiung" sort="Lin, Wen Hsiung" uniqKey="Lin W" first="Wen-Hsiung" last="Lin">Wen-Hsiung Lin</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Institute of Information Science, Academia Sinica</s1>
<s2>Taipei</s2>
<s3>TWN</s3>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>Taïwan</country>
<wicri:noRegion>Taipei</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Fu Chang" sort="Fu Chang" uniqKey="Fu Chang" last="Fu Chang">FU CHANG</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Institute of Information Science, Academia Sinica</s1>
<s2>Taipei</s2>
<s3>TWN</s3>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>Taïwan</country>
<wicri:noRegion>Taipei</wicri:noRegion>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">10-0118750</idno>
<date when="2010">2010</date>
<idno type="stanalyst">PASCAL 10-0118750 INIST</idno>
<idno type="RBID">Pascal:10-0118750</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000200</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000577</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000174</idno>
<idno type="wicri:doubleKey">0031-3203:2010:Chou C:a:binarization:method</idno>
<idno type="wicri:Area/Main/Merge">000805</idno>
<idno type="wicri:Area/Main/Curation">000799</idno>
<idno type="wicri:Area/Main/Exploration">000799</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">A binarization method with learning-built rules for document images produced by cameras</title>
<author><name sortKey="Chou, Chien Hsing" sort="Chou, Chien Hsing" uniqKey="Chou C" first="Chien-Hsing" last="Chou">Chien-Hsing Chou</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Electrical Engineering, Tamkang University</s1>
<s3>TWN</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
<country>Taïwan</country>
<wicri:noRegion>Department of Electrical Engineering, Tamkang University</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Lin, Wen Hsiung" sort="Lin, Wen Hsiung" uniqKey="Lin W" first="Wen-Hsiung" last="Lin">Wen-Hsiung Lin</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Institute of Information Science, Academia Sinica</s1>
<s2>Taipei</s2>
<s3>TWN</s3>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>Taïwan</country>
<wicri:noRegion>Taipei</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Fu Chang" sort="Fu Chang" uniqKey="Fu Chang" last="Fu Chang">FU CHANG</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Institute of Information Science, Academia Sinica</s1>
<s2>Taipei</s2>
<s3>TWN</s3>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>Taïwan</country>
<wicri:noRegion>Taipei</wicri:noRegion>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Pattern recognition</title>
<title level="j" type="abbreviated">Pattern recogn.</title>
<idno type="ISSN">0031-3203</idno>
<imprint><date when="2010">2010</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">Pattern recognition</title>
<title level="j" type="abbreviated">Pattern recogn.</title>
<idno type="ISSN">0031-3203</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Adaptive method</term>
<term>Automatic classification</term>
<term>Binary image</term>
<term>Brightness</term>
<term>Decision rule</term>
<term>Document image processing</term>
<term>Image processing</term>
<term>Image quality</term>
<term>Learning</term>
<term>Multilabeling</term>
<term>Optical character recognition</term>
<term>Pattern recognition</term>
<term>Performance evaluation</term>
<term>Signal classification</term>
<term>Statistical method</term>
<term>Support vector machine</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Apprentissage</term>
<term>Traitement image document</term>
<term>Brillance</term>
<term>Méthode statistique</term>
<term>Règle décision</term>
<term>Qualité image</term>
<term>Reconnaissance optique caractère</term>
<term>Evaluation performance</term>
<term>Méthode adaptative</term>
<term>Image binaire</term>
<term>Traitement image</term>
<term>Machine vecteur support</term>
<term>Reconnaissance forme</term>
<term>Classification signal</term>
<term>Classification automatique</term>
<term>Etiquetage multiple</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">In this paper, we propose a novel binarization method for document images produced by cameras. Such images often have varying degrees of brightness and require more careful treatment than merely applying a statistical method to obtain a threshold value. To resolve the problem, the proposed method divides an image into several regions and decides how to binarize each region. The decision rules are derived from a learning process that takes training images as input. Tests on images produced under normal and inadequate illumination conditions show that our method yields better visual quality and better OCR performance than three global binarization methods and four locally adaptive binarization methods.</div>
</front>
</TEI>
<affiliations><list><country><li>Taïwan</li>
</country>
</list>
<tree><country name="Taïwan"><noRegion><name sortKey="Chou, Chien Hsing" sort="Chou, Chien Hsing" uniqKey="Chou C" first="Chien-Hsing" last="Chou">Chien-Hsing Chou</name>
</noRegion>
<name sortKey="Fu Chang" sort="Fu Chang" uniqKey="Fu Chang" last="Fu Chang">FU CHANG</name>
<name sortKey="Lin, Wen Hsiung" sort="Lin, Wen Hsiung" uniqKey="Lin W" first="Wen-Hsiung" last="Lin">Wen-Hsiung Lin</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 000799 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000799 | 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:10-0118750
   |texte=   A binarization method with learning-built rules for document images produced by cameras
}}

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

	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.

Serveur d'exploration sur l'OCR

A binarization method with learning-built rules for document images produced by cameras

A binarization method with learning-built rules for document images produced by cameras

Source :

Descripteurs français

English descriptors

Abstract

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

Le document en format XML

Pour manipuler ce document sous Unix (Dilib)

Pour mettre un lien sur cette page dans le réseau Wicri