Cursive Arabic script segmentation and recognition system
Identifieur interne : 001406 ( Main/Exploration ); précédent : 001405; suivant : 001407Cursive Arabic script segmentation and recognition system
Auteurs : T. Sari [Algérie] ; M. Sellami [Algérie]Source :
- International journal of computers & applications [ 1206-212X ] ; 2005.
Descripteurs français
- Pascal (Inist)
- Arabe, Segmentation, Reconnaissance caractère, Reconnaissance optique caractère, Algorithme, Mot isolé, Caractère manuscrit, Système expert, Extraction caractéristique, Evaluation performance, Réseau neuronal, Reconnaissance caractère manuscrit, Reconnaissance forme, Traitement signal, Analyse contour.
English descriptors
- KwdEn :
Abstract
Character segmentation is a necessary preprocessing step for character recognition in many OCR systems. It is an important step because incorrectly segmented characters will not be recognized correctly. The most difficult case in character segmentation is cursive script. The scripted nature of Arabic written language poses some high challenges for automatic character segmentation and recognition. The authors present a new Character Segmentation Algorithm (ACSA) of Arabic script. The developed segmentation algorithm yields the splitting up of isolated handwritten words in perfectly separated characters. It is based on topological rules, which are constructed at the feature extraction phase. To increase ACSA's performances, it was combined it with an Arabic characters recognition system, RECAM.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000472
- to stream PascalFrancis, to step Curation: 000317
- to stream PascalFrancis, to step Checkpoint: 000420
- to stream Main, to step Merge: 001450
- to stream Main, to step Curation: 001406
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Cursive Arabic script segmentation and recognition system</title><author><name sortKey="Sari, T" sort="Sari, T" uniqKey="Sari T" first="T." last="Sari">T. Sari</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Research Laboratory in Computer Science-LRI-Annaba, Annaba University</s1><s3>DZA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>Algérie</country><wicri:noRegion>Research Laboratory in Computer Science-LRI-Annaba, Annaba University</wicri:noRegion></affiliation></author><author><name sortKey="Sellami, M" sort="Sellami, M" uniqKey="Sellami M" first="M." last="Sellami">M. Sellami</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Research Laboratory in Computer Science-LRI-Annaba, Annaba University</s1><s3>DZA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>Algérie</country><wicri:noRegion>Research Laboratory in Computer Science-LRI-Annaba, Annaba University</wicri:noRegion></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">INIST</idno><idno type="inist">05-0282645</idno><date when="2005">2005</date><idno type="stanalyst">PASCAL 05-0282645 INIST</idno><idno type="RBID">Pascal:05-0282645</idno><idno type="wicri:Area/PascalFrancis/Corpus">000472</idno><idno type="wicri:Area/PascalFrancis/Curation">000317</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000420</idno><idno type="wicri:doubleKey">1206-212X:2005:Sari T:cursive:arabic:script</idno><idno type="wicri:Area/Main/Merge">001450</idno><idno type="wicri:Area/Main/Curation">001406</idno><idno type="wicri:Area/Main/Exploration">001406</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Cursive Arabic script segmentation and recognition system</title><author><name sortKey="Sari, T" sort="Sari, T" uniqKey="Sari T" first="T." last="Sari">T. Sari</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Research Laboratory in Computer Science-LRI-Annaba, Annaba University</s1><s3>DZA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>Algérie</country><wicri:noRegion>Research Laboratory in Computer Science-LRI-Annaba, Annaba University</wicri:noRegion></affiliation></author><author><name sortKey="Sellami, M" sort="Sellami, M" uniqKey="Sellami M" first="M." last="Sellami">M. Sellami</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Research Laboratory in Computer Science-LRI-Annaba, Annaba University</s1><s3>DZA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>Algérie</country><wicri:noRegion>Research Laboratory in Computer Science-LRI-Annaba, Annaba University</wicri:noRegion></affiliation></author></analytic><series><title level="j" type="main">International journal of computers & applications</title><title level="j" type="abbreviated">Int. j. comput. appl.</title><idno type="ISSN">1206-212X</idno><imprint><date when="2005">2005</date></imprint></series></biblStruct></sourceDesc><seriesStmt><title level="j" type="main">International journal of computers & applications</title><title level="j" type="abbreviated">Int. j. comput. appl.</title><idno type="ISSN">1206-212X</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithm</term><term>Arabic</term><term>Character recognition</term><term>Contour analysis</term><term>Expert system</term><term>Feature extraction</term><term>Handwritten character recognition</term><term>Isolated word</term><term>Manuscript character</term><term>Neural network</term><term>Optical character recognition</term><term>Pattern recognition</term><term>Performance evaluation</term><term>Segmentation</term><term>Signal processing</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Arabe</term><term>Segmentation</term><term>Reconnaissance caractère</term><term>Reconnaissance optique caractère</term><term>Algorithme</term><term>Mot isolé</term><term>Caractère manuscrit</term><term>Système expert</term><term>Extraction caractéristique</term><term>Evaluation performance</term><term>Réseau neuronal</term><term>Reconnaissance caractère manuscrit</term><term>Reconnaissance forme</term><term>Traitement signal</term><term>Analyse contour</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Character segmentation is a necessary preprocessing step for character recognition in many OCR systems. It is an important step because incorrectly segmented characters will not be recognized correctly. The most difficult case in character segmentation is cursive script. The scripted nature of Arabic written language poses some high challenges for automatic character segmentation and recognition. The authors present a new Character Segmentation Algorithm (ACSA) of Arabic script. The developed segmentation algorithm yields the splitting up of isolated handwritten words in perfectly separated characters. It is based on topological rules, which are constructed at the feature extraction phase. To increase ACSA's performances, it was combined it with an Arabic characters recognition system, RECAM.</div></front></TEI><affiliations><list><country><li>Algérie</li></country></list><tree><country name="Algérie"><noRegion><name sortKey="Sari, T" sort="Sari, T" uniqKey="Sari T" first="T." last="Sari">T. Sari</name></noRegion><name sortKey="Sellami, M" sort="Sellami, M" uniqKey="Sellami M" first="M." last="Sellami">M. Sellami</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 001406 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001406 | 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:05-0282645
|texte= Cursive Arabic script segmentation and recognition system
}}
| This area was generated with Dilib version V0.6.32. |  |