A new approach for text segmentation using a stroke filter
Identifieur interne : 000D35 ( Main/Exploration ); précédent : 000D34; suivant : 000D36A new approach for text segmentation using a stroke filter
Auteurs : Cheolkon Jung [Corée du Sud] ; QIFENG LIU [Corée du Sud] ; Joongkyu Kim [Corée du Sud]Source :
- Signal processing [ 0165-1684 ] ; 2008.
Descripteurs français
- Pascal (Inist)
- Wicri :
- topic : Base de données.
English descriptors
- KwdEn :
Abstract
We propose a new method for achieving robust text segmentation in images by using a stroke filter. It is known that to segment text accurately and robustly from a complex background is a very difficult task. Most of the existing methods are sensitive to text color, size, font, and background clutter, because they use simple segmentation methods or require prior knowledge about text shape. In this paper, we attempt to consider the intrinsic characteristics of the text by using the stroke filter and design a new and robust algorithm for text segmentation. First, we describe the stroke filter briefly based on local region analysis. Second, the determination of text color polarity and local region growing procedures are performed successively based on the response of the stroke filter. Finally, the feedback procedure by the recognition score from an optical character recognition (OCR) module is used to improve the performance of text segmentation. By means of experiments on a large database, we demonstrate that the performance of our method is quite impressive from the viewpoints of the accuracy and robustness.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000284
- to stream PascalFrancis, to step Curation: 000500
- to stream PascalFrancis, to step Checkpoint: 000257
- to stream Main, to step Merge: 000D47
- to stream Main, to step Curation: 000D35
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">A new approach for text segmentation using a stroke filter</title><author><name sortKey="Jung, Cheolkon" sort="Jung, Cheolkon" uniqKey="Jung C" first="Cheolkon" last="Jung">Cheolkon Jung</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Information and Communication Engineering, Sungkyunkwan University, 300 Cheoncheon-dong</s1><s2>Suwon, Kyunggido 440-746</s2><s3>KOR</s3><sZ>1 aut.</sZ><sZ>3 aut.</sZ></inist:fA14><country>Corée du Sud</country><wicri:noRegion>Suwon, Kyunggido 440-746</wicri:noRegion></affiliation></author><author><name sortKey="Qifeng Liu" sort="Qifeng Liu" uniqKey="Qifeng Liu" last="Qifeng Liu">QIFENG LIU</name><affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Samsung Advanced Institute of Technology</s1><s2>Yongin, Kyunggido 446-712</s2><s3>KOR</s3><sZ>2 aut.</sZ></inist:fA14><country>Corée du Sud</country><wicri:noRegion>Samsung Advanced Institute of Technology</wicri:noRegion></affiliation></author><author><name sortKey="Kim, Joongkyu" sort="Kim, Joongkyu" uniqKey="Kim J" first="Joongkyu" last="Kim">Joongkyu Kim</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Information and Communication Engineering, Sungkyunkwan University, 300 Cheoncheon-dong</s1><s2>Suwon, Kyunggido 440-746</s2><s3>KOR</s3><sZ>1 aut.</sZ><sZ>3 aut.</sZ></inist:fA14><country>Corée du Sud</country><wicri:noRegion>Suwon, Kyunggido 440-746</wicri:noRegion></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">INIST</idno><idno type="inist">08-0219729</idno><date when="2008">2008</date><idno type="stanalyst">PASCAL 08-0219729 INIST</idno><idno type="RBID">Pascal:08-0219729</idno><idno type="wicri:Area/PascalFrancis/Corpus">000284</idno><idno type="wicri:Area/PascalFrancis/Curation">000500</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000257</idno><idno type="wicri:doubleKey">0165-1684:2008:Jung C:a:new:approach</idno><idno type="wicri:Area/Main/Merge">000D47</idno><idno type="wicri:Area/Main/Curation">000D35</idno><idno type="wicri:Area/Main/Exploration">000D35</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">A new approach for text segmentation using a stroke filter</title><author><name sortKey="Jung, Cheolkon" sort="Jung, Cheolkon" uniqKey="Jung C" first="Cheolkon" last="Jung">Cheolkon Jung</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Information and Communication Engineering, Sungkyunkwan University, 300 Cheoncheon-dong</s1><s2>Suwon, Kyunggido 440-746</s2><s3>KOR</s3><sZ>1 aut.</sZ><sZ>3 aut.</sZ></inist:fA14><country>Corée du Sud</country><wicri:noRegion>Suwon, Kyunggido 440-746</wicri:noRegion></affiliation></author><author><name sortKey="Qifeng Liu" sort="Qifeng Liu" uniqKey="Qifeng Liu" last="Qifeng Liu">QIFENG LIU</name><affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Samsung Advanced Institute of Technology</s1><s2>Yongin, Kyunggido 446-712</s2><s3>KOR</s3><sZ>2 aut.</sZ></inist:fA14><country>Corée du Sud</country><wicri:noRegion>Samsung Advanced Institute of Technology</wicri:noRegion></affiliation></author><author><name sortKey="Kim, Joongkyu" sort="Kim, Joongkyu" uniqKey="Kim J" first="Joongkyu" last="Kim">Joongkyu Kim</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Information and Communication Engineering, Sungkyunkwan University, 300 Cheoncheon-dong</s1><s2>Suwon, Kyunggido 440-746</s2><s3>KOR</s3><sZ>1 aut.</sZ><sZ>3 aut.</sZ></inist:fA14><country>Corée du Sud</country><wicri:noRegion>Suwon, Kyunggido 440-746</wicri:noRegion></affiliation></author></analytic><series><title level="j" type="main">Signal processing</title><title level="j" type="abbreviated">Signal process.</title><idno type="ISSN">0165-1684</idno><imprint><date when="2008">2008</date></imprint></series></biblStruct></sourceDesc><seriesStmt><title level="j" type="main">Signal processing</title><title level="j" type="abbreviated">Signal process.</title><idno type="ISSN">0165-1684</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Accuracy</term><term>Algorithm</term><term>Background</term><term>Clutter</term><term>Database</term><term>Information extraction</term><term>Information processing</term><term>Optical character recognition</term><term>Pattern recognition</term><term>Performance evaluation</term><term>Robustness</term><term>Segmentation</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Segmentation</term><term>Fouillis écho</term><term>Algorithme</term><term>Reconnaissance optique caractère</term><term>Evaluation performance</term><term>Base de données</term><term>Précision</term><term>Robustesse</term><term>Extraction information</term><term>Reconnaissance forme</term><term>Traitement information</term><term>Arrière plan</term></keywords><keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Base de données</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">We propose a new method for achieving robust text segmentation in images by using a stroke filter. It is known that to segment text accurately and robustly from a complex background is a very difficult task. Most of the existing methods are sensitive to text color, size, font, and background clutter, because they use simple segmentation methods or require prior knowledge about text shape. In this paper, we attempt to consider the intrinsic characteristics of the text by using the stroke filter and design a new and robust algorithm for text segmentation. First, we describe the stroke filter briefly based on local region analysis. Second, the determination of text color polarity and local region growing procedures are performed successively based on the response of the stroke filter. Finally, the feedback procedure by the recognition score from an optical character recognition (OCR) module is used to improve the performance of text segmentation. By means of experiments on a large database, we demonstrate that the performance of our method is quite impressive from the viewpoints of the accuracy and robustness.</div></front></TEI><affiliations><list><country><li>Corée du Sud</li></country></list><tree><country name="Corée du Sud"><noRegion><name sortKey="Jung, Cheolkon" sort="Jung, Cheolkon" uniqKey="Jung C" first="Cheolkon" last="Jung">Cheolkon Jung</name></noRegion><name sortKey="Kim, Joongkyu" sort="Kim, Joongkyu" uniqKey="Kim J" first="Joongkyu" last="Kim">Joongkyu Kim</name><name sortKey="Qifeng Liu" sort="Qifeng Liu" uniqKey="Qifeng Liu" last="Qifeng Liu">QIFENG LIU</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 000D35 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000D35 | 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:08-0219729
|texte= A new approach for text segmentation using a stroke filter
}}
| This area was generated with Dilib version V0.6.32. |  |