Structural and syntactic techniques for recognition of ethiopic characters
Identifieur interne : 001169 ( Main/Merge ); précédent : 001168; suivant : 001170Structural and syntactic techniques for recognition of ethiopic characters
Auteurs : Yaregal Assabie [Suède] ; Josef Bigun [Suède]Source :
- Lecture notes in computer science [ 0302-9743 ] ; 2006.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
OCR technology of Latin scripts is well advanced in comparison to other scripts. However, the available results from Latin are not always sufficient to directly adopt them for other scripts such as the Ethiopic script. In this paper, we propose a novel approach that uses structural and syntactic techniques for recognition of Ethiopic characters. We reveal that primitive structures and their spatial relationships form a unique set of patterns for each character. The relationships of primitives are represented by a special tree structure, which is also used to generate a pattern. A knowledge base of the alphabet that stores possibly occurring patterns for each character is built. Recognition is then achieved by matching the generated pattern against each pattern in the knowledge base. Structural features are extracted using direction field tensor. Experimental results are reported, and the recognition system is insensitive to variations on font types, sizes and styles.
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000324
- to stream PascalFrancis, to step Curation: 000462
- to stream PascalFrancis, to step Checkpoint: 000308
Links to Exploration step
Pascal:07-0464297Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Structural and syntactic techniques for recognition of ethiopic characters</title><author><name sortKey="Assabie, Yaregal" sort="Assabie, Yaregal" uniqKey="Assabie Y" first="Yaregal" last="Assabie">Yaregal Assabie</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Information Science, Computer and Electrical Engineering Halmstad University</s1><s2>301 18 Halmstad</s2><s3>SWE</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>Suède</country><wicri:noRegion>301 18 Halmstad</wicri:noRegion></affiliation></author><author><name sortKey="Bigun, Josef" sort="Bigun, Josef" uniqKey="Bigun J" first="Josef" last="Bigun">Josef Bigun</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Information Science, Computer and Electrical Engineering Halmstad University</s1><s2>301 18 Halmstad</s2><s3>SWE</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>Suède</country><wicri:noRegion>301 18 Halmstad</wicri:noRegion></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">INIST</idno><idno type="inist">07-0464297</idno><date when="2006">2006</date><idno type="stanalyst">PASCAL 07-0464297 INIST</idno><idno type="RBID">Pascal:07-0464297</idno><idno type="wicri:Area/PascalFrancis/Corpus">000324</idno><idno type="wicri:Area/PascalFrancis/Curation">000462</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000308</idno><idno type="wicri:doubleKey">0302-9743:2006:Assabie Y:structural:and:syntactic</idno><idno type="wicri:Area/Main/Merge">001169</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Structural and syntactic techniques for recognition of ethiopic characters</title><author><name sortKey="Assabie, Yaregal" sort="Assabie, Yaregal" uniqKey="Assabie Y" first="Yaregal" last="Assabie">Yaregal Assabie</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Information Science, Computer and Electrical Engineering Halmstad University</s1><s2>301 18 Halmstad</s2><s3>SWE</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>Suède</country><wicri:noRegion>301 18 Halmstad</wicri:noRegion></affiliation></author><author><name sortKey="Bigun, Josef" sort="Bigun, Josef" uniqKey="Bigun J" first="Josef" last="Bigun">Josef Bigun</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Information Science, Computer and Electrical Engineering Halmstad University</s1><s2>301 18 Halmstad</s2><s3>SWE</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>Suède</country><wicri:noRegion>301 18 Halmstad</wicri:noRegion></affiliation></author></analytic><series><title level="j" type="main">Lecture notes in computer science</title><idno type="ISSN">0302-9743</idno><imprint><date when="2006">2006</date></imprint></series></biblStruct></sourceDesc><seriesStmt><title level="j" type="main">Lecture notes in computer science</title><idno type="ISSN">0302-9743</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Character recognition</term><term>Image processing</term><term>Knowledge base</term><term>Optical character recognition</term><term>Pattern extraction</term><term>Pattern matching</term><term>Pattern recognition</term><term>Statistical analysis</term><term>Structural analysis</term><term>Syntactic analysis</term><term>Tree structure</term><term>Tree structured method</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Analyse statistique</term><term>Analyse structurale</term><term>Analyse syntaxique</term><term>Reconnaissance caractère</term><term>Reconnaissance forme</term><term>Traitement image</term><term>Reconnaissance optique caractère</term><term>Concordance forme</term><term>Méthode arborescente</term><term>Structure arborescente</term><term>Base connaissance</term><term>Extraction forme</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">OCR technology of Latin scripts is well advanced in comparison to other scripts. However, the available results from Latin are not always sufficient to directly adopt them for other scripts such as the Ethiopic script. In this paper, we propose a novel approach that uses structural and syntactic techniques for recognition of Ethiopic characters. We reveal that primitive structures and their spatial relationships form a unique set of patterns for each character. The relationships of primitives are represented by a special tree structure, which is also used to generate a pattern. A knowledge base of the alphabet that stores possibly occurring patterns for each character is built. Recognition is then achieved by matching the generated pattern against each pattern in the knowledge base. Structural features are extracted using direction field tensor. Experimental results are reported, and the recognition system is insensitive to variations on font types, sizes and styles.</div></front></TEI><affiliations><list><country><li>Suède</li></country></list><tree><country name="Suède"><noRegion><name sortKey="Assabie, Yaregal" sort="Assabie, Yaregal" uniqKey="Assabie Y" first="Yaregal" last="Assabie">Yaregal Assabie</name></noRegion><name sortKey="Bigun, Josef" sort="Bigun, Josef" uniqKey="Bigun J" first="Josef" last="Bigun">Josef Bigun</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001169 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 001169 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= Main
|étape= Merge
|type= RBID
|clé= Pascal:07-0464297
|texte= Structural and syntactic techniques for recognition of ethiopic characters
}}
| This area was generated with Dilib version V0.6.32. |  |