Character location in scene images from digital camera
Identifieur interne : 001805 ( Main/Exploration ); précédent : 001804; suivant : 001806Character location in scene images from digital camera
Auteurs : K. Wang [République populaire de Chine] ; J. A. KangasSource :
- Pattern Recognition [ 0031-3203 ] ; 2003.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
In this paper, a robust, connected-component-based character locating method is presented. It is an important part of an optical character recognition (OCR) system. Color clustering is used to separate the color image into homogeneous color layers. Next, for each color layer, every connected component in color layers is analyzed using black adjacency graph (BAG), and the component-bounding box is computed. Then, for coarse detection of characters, an aligning-and-merging-analysis (AMA) scheme is proposed to locate all the potential characters using the information about the bounding boxes of connected components in all color layers. Finally, to eliminate false characters, a four-step identification of characters is used. The experimental results in this paper have proven that the method is effective. © 2003 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000609
- to stream PascalFrancis, to step Curation: 000182
- to stream PascalFrancis, to step Checkpoint: 000570
- to stream Main, to step Merge: 001884
- to stream Main, to step Curation: 001805
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Character location in scene images from digital camera</title><author><name sortKey="Wang, K" sort="Wang, K" uniqKey="Wang K" first="K." last="Wang">K. Wang</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Nokia Research Center</s1><s2>Beijing 100013</s2><s3>CHN</s3><sZ>1 aut.</sZ></inist:fA14><country>République populaire de Chine</country><placeName><settlement type="city">Pékin</settlement></placeName></affiliation></author><author><name sortKey="Kangas, J A" sort="Kangas, J A" uniqKey="Kangas J" first="J. A." last="Kangas">J. A. Kangas</name></author></titleStmt><publicationStmt><idno type="wicri:source">INIST</idno><idno type="inist">03-0353388</idno><date when="2003">2003</date><idno type="stanalyst">PASCAL 03-0353388 EI</idno><idno type="RBID">Pascal:03-0353388</idno><idno type="wicri:Area/PascalFrancis/Corpus">000609</idno><idno type="wicri:Area/PascalFrancis/Curation">000182</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000570</idno><idno type="wicri:doubleKey">0031-3203:2003:Wang K:character:location:in</idno><idno type="wicri:Area/Main/Merge">001884</idno><idno type="wicri:Area/Main/Curation">001805</idno><idno type="wicri:Area/Main/Exploration">001805</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Character location in scene images from digital camera</title><author><name sortKey="Wang, K" sort="Wang, K" uniqKey="Wang K" first="K." last="Wang">K. Wang</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Nokia Research Center</s1><s2>Beijing 100013</s2><s3>CHN</s3><sZ>1 aut.</sZ></inist:fA14><country>République populaire de Chine</country><placeName><settlement type="city">Pékin</settlement></placeName></affiliation></author><author><name sortKey="Kangas, J A" sort="Kangas, J A" uniqKey="Kangas J" first="J. A." last="Kangas">J. A. Kangas</name></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="2003">2003</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>Cameras</term><term>Color image processing</term><term>Digital cameras</term><term>Optical character recognition</term><term>Pattern recognition</term><term>Theory</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Théorie</term><term>Appareil photographique</term><term>Reconnaissance optique caractère</term><term>Traitement image couleur</term><term>Reconnaissance forme</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">In this paper, a robust, connected-component-based character locating method is presented. It is an important part of an optical character recognition (OCR) system. Color clustering is used to separate the color image into homogeneous color layers. Next, for each color layer, every connected component in color layers is analyzed using black adjacency graph (BAG), and the component-bounding box is computed. Then, for coarse detection of characters, an aligning-and-merging-analysis (AMA) scheme is proposed to locate all the potential characters using the information about the bounding boxes of connected components in all color layers. Finally, to eliminate false characters, a four-step identification of characters is used. The experimental results in this paper have proven that the method is effective. © 2003 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.</div></front></TEI><affiliations><list><country><li>République populaire de Chine</li></country><settlement><li>Pékin</li></settlement></list><tree><noCountry><name sortKey="Kangas, J A" sort="Kangas, J A" uniqKey="Kangas J" first="J. A." last="Kangas">J. A. Kangas</name></noCountry><country name="République populaire de Chine"><noRegion><name sortKey="Wang, K" sort="Wang, K" uniqKey="Wang K" first="K." last="Wang">K. Wang</name></noRegion></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 001805 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001805 | 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:03-0353388
|texte= Character location in scene images from digital camera
}}
| This area was generated with Dilib version V0.6.32. |  |