Feature extraction methods for character recognition : a survey
Identifieur interne : 002887 ( Main/Exploration ); précédent : 002886; suivant : 002888Feature extraction methods for character recognition : a survey
Auteurs : D. Trier [Norvège] ; A. K. Jain ; T. Taxt [Norvège]Source :
- Pattern recognition [ 0031-3203 ] ; 1996.
Descripteurs français
- Pascal (Inist)
English descriptors
Abstract
This paper presents an overview of feature extraction methods for off-line recognition of segmented (isolated) characters. Selection of a feature extraction method is probably the single most important factor in achieving high recognition performance in character recognition systems. Different feature extraction methods are designed for different representations of the characters, such as solid binary characters, character contours, skeletons (thinned characters) or gray-level subimages of each individual character. The feature extraction methods are discussed in terms of invariance properties, reconstructability and expected distortions and variability of the characters. The problem of choosing the appropriate feature extraction method for a given application is also discussed. When a few promising feature extraction methods have been identified, they need to be evaluated experimentally to find the best method for the given application.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000A11
- to stream PascalFrancis, to step Curation: 000987
- to stream PascalFrancis, to step Checkpoint: 000951
- to stream Main, to step Merge: 002A38
- to stream Main, to step Curation: 002887
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Feature extraction methods for character recognition : a survey</title><author><name sortKey="Trier, D" sort="Trier, D" uniqKey="Trier " first=" D." last="Trier"> D. Trier</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Informatics, University of Oslo, P.O. Box 1080 Blindern</s1><s2>0316 Oslo</s2><s3>NOR</s3><sZ>1 aut.</sZ><sZ>3 aut.</sZ></inist:fA14><country>Norvège</country><wicri:noRegion>0316 Oslo</wicri:noRegion></affiliation></author><author><name sortKey="Jain, A K" sort="Jain, A K" uniqKey="Jain A" first="A. K." last="Jain">A. K. Jain</name></author><author><name sortKey="Taxt, T" sort="Taxt, T" uniqKey="Taxt T" first="T." last="Taxt">T. Taxt</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Informatics, University of Oslo, P.O. Box 1080 Blindern</s1><s2>0316 Oslo</s2><s3>NOR</s3><sZ>1 aut.</sZ><sZ>3 aut.</sZ></inist:fA14><country>Norvège</country><wicri:noRegion>0316 Oslo</wicri:noRegion></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">INIST</idno><idno type="inist">96-0217076</idno><date when="1996">1996</date><idno type="stanalyst">PASCAL 96-0217076 INIST</idno><idno type="RBID">Pascal:96-0217076</idno><idno type="wicri:Area/PascalFrancis/Corpus">000A11</idno><idno type="wicri:Area/PascalFrancis/Curation">000987</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000951</idno><idno type="wicri:doubleKey">0031-3203:1996:Trier :feature:extraction:methods</idno><idno type="wicri:Area/Main/Merge">002A38</idno><idno type="wicri:Area/Main/Curation">002887</idno><idno type="wicri:Area/Main/Exploration">002887</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Feature extraction methods for character recognition : a survey</title><author><name sortKey="Trier, D" sort="Trier, D" uniqKey="Trier " first=" D." last="Trier"> D. Trier</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Informatics, University of Oslo, P.O. Box 1080 Blindern</s1><s2>0316 Oslo</s2><s3>NOR</s3><sZ>1 aut.</sZ><sZ>3 aut.</sZ></inist:fA14><country>Norvège</country><wicri:noRegion>0316 Oslo</wicri:noRegion></affiliation></author><author><name sortKey="Jain, A K" sort="Jain, A K" uniqKey="Jain A" first="A. K." last="Jain">A. K. Jain</name></author><author><name sortKey="Taxt, T" sort="Taxt, T" uniqKey="Taxt T" first="T." last="Taxt">T. Taxt</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Informatics, University of Oslo, P.O. Box 1080 Blindern</s1><s2>0316 Oslo</s2><s3>NOR</s3><sZ>1 aut.</sZ><sZ>3 aut.</sZ></inist:fA14><country>Norvège</country><wicri:noRegion>0316 Oslo</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="1996">1996</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>Character recognition</term><term>Image recognition</term><term>Invariance</term><term>OCR</term><term>Pattern extraction</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Extraction forme</term><term>Reconnaissance caractère</term><term>Reconnaissance image</term><term>Invariance</term><term>Reconstructability</term><term>Character representation</term><term>OCR</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">This paper presents an overview of feature extraction methods for off-line recognition of segmented (isolated) characters. Selection of a feature extraction method is probably the single most important factor in achieving high recognition performance in character recognition systems. Different feature extraction methods are designed for different representations of the characters, such as solid binary characters, character contours, skeletons (thinned characters) or gray-level subimages of each individual character. The feature extraction methods are discussed in terms of invariance properties, reconstructability and expected distortions and variability of the characters. The problem of choosing the appropriate feature extraction method for a given application is also discussed. When a few promising feature extraction methods have been identified, they need to be evaluated experimentally to find the best method for the given application.</div></front></TEI><affiliations><list><country><li>Norvège</li></country></list><tree><noCountry><name sortKey="Jain, A K" sort="Jain, A K" uniqKey="Jain A" first="A. K." last="Jain">A. K. Jain</name></noCountry><country name="Norvège"><noRegion><name sortKey="Trier, D" sort="Trier, D" uniqKey="Trier " first=" D." last="Trier"> D. Trier</name></noRegion><name sortKey="Taxt, T" sort="Taxt, T" uniqKey="Taxt T" first="T." last="Taxt">T. Taxt</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 002887 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 002887 | 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:96-0217076
|texte= Feature extraction methods for character recognition : a survey
}}
| This area was generated with Dilib version V0.6.32. |  |