Compound character recognition by run number based metric distance
Identifieur interne : 002316 ( Main/Exploration ); précédent : 002315; suivant : 002317Compound character recognition by run number based metric distance
Auteurs : U. Garain [Inde] ; Bidyut Baran Chaudhuri [Inde]Source :
- SPIE proceedings series [ 1017-2653 ] ; 1998.
Descripteurs français
- Pascal (Inist)
- Wicri :
English descriptors
Abstract
This paper concerns automatic OCR of Bangla, a major Indian Language Script which is the fourth most popular script in the world. A Bangla OCR system has to recognize about 300 graphemic shapes among which 250 compound characters have quite complex stroke patterns. For recognition of such compound characters, feature based approaches are less reliable and template based approaches are less flexible to size and style variation of character font. We combine the positive aspects of feature based and template based approaches. Here we propose a run number based normalized template matching technique for compound character recognition. Run number vectors for both horizontal and vertical scanning are computed. As the number of scans may vary from pattern to pattern, we normalize and abbreviate the vector. We prove that this normalized and abbreviated vector induces metric distance. Moreover, this vector is invariant to scaling, insensitive to character style variation and more effective for more complex-shaped characters than simple-shaped ones. We use this vector representation for matching within a group of compound characters. We notice that the matching is more efficient if the vector is reorganized with respect to the centroid of the pattern. We have tested our approach on a large set of segmented compound characters at different point sizes as well as different styles. Italic characters are subject to preprocessing. The overall correct recognition rate is 99.69%.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000867
- to stream PascalFrancis, to step Curation: 000B29
- to stream PascalFrancis, to step Checkpoint: 000847
- to stream Main, to step Merge: 002441
- to stream Main, to step Curation: 002316
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Compound character recognition by run number based metric distance</title>
<author><name sortKey="Garain, U" sort="Garain, U" uniqKey="Garain U" first="U." last="Garain">U. Garain</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Computer Vision & Pattern Recognition Unit, Indian Statistical Institute, 203, B. T. Road</s1>
<s2>Calcutta 700 035</s2>
<s3>IND</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Inde</country>
<wicri:noRegion>Calcutta 700 035</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Chaudhuri, B B" sort="Chaudhuri, B B" uniqKey="Chaudhuri B" first="B. B." last="Chaudhuri">Bidyut Baran Chaudhuri</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Computer Vision & Pattern Recognition Unit, Indian Statistical Institute, 203, B. T. Road</s1>
<s2>Calcutta 700 035</s2>
<s3>IND</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Inde</country>
<wicri:noRegion>Calcutta 700 035</wicri:noRegion>
<placeName><settlement type="city">Calcutta</settlement>
<region type="province">Bengale-Occidental</region>
</placeName>
<orgName type="lab" n="5">Institut indien de statistiques</orgName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">98-0385607</idno>
<date when="1998">1998</date>
<idno type="stanalyst">PASCAL 98-0385607 INIST</idno>
<idno type="RBID">Pascal:98-0385607</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000867</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000B29</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000847</idno>
<idno type="wicri:doubleKey">1017-2653:1998:Garain U:compound:character:recognition</idno>
<idno type="wicri:Area/Main/Merge">002441</idno>
<idno type="wicri:Area/Main/Curation">002316</idno>
<idno type="wicri:Area/Main/Exploration">002316</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Compound character recognition by run number based metric distance</title>
<author><name sortKey="Garain, U" sort="Garain, U" uniqKey="Garain U" first="U." last="Garain">U. Garain</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Computer Vision & Pattern Recognition Unit, Indian Statistical Institute, 203, B. T. Road</s1>
<s2>Calcutta 700 035</s2>
<s3>IND</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Inde</country>
<wicri:noRegion>Calcutta 700 035</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Chaudhuri, B B" sort="Chaudhuri, B B" uniqKey="Chaudhuri B" first="B. B." last="Chaudhuri">Bidyut Baran Chaudhuri</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Computer Vision & Pattern Recognition Unit, Indian Statistical Institute, 203, B. T. Road</s1>
<s2>Calcutta 700 035</s2>
<s3>IND</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Inde</country>
<wicri:noRegion>Calcutta 700 035</wicri:noRegion>
<placeName><settlement type="city">Calcutta</settlement>
<region type="province">Bengale-Occidental</region>
</placeName>
<orgName type="lab" n="5">Institut indien de statistiques</orgName>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">SPIE proceedings series</title>
<idno type="ISSN">1017-2653</idno>
<imprint><date when="1998">1998</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">SPIE proceedings series</title>
<idno type="ISSN">1017-2653</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Character recognition</term>
<term>India</term>
<term>Language</term>
<term>Optical character recognition</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Inde</term>
<term>Langage</term>
<term>Reconnaissance optique caractère</term>
<term>Reconnaissance caractère</term>
</keywords>
<keywords scheme="Wicri" type="geographic" xml:lang="fr"><term>Inde</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Langage</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">This paper concerns automatic OCR of Bangla, a major Indian Language Script which is the fourth most popular script in the world. A Bangla OCR system has to recognize about 300 graphemic shapes among which 250 compound characters have quite complex stroke patterns. For recognition of such compound characters, feature based approaches are less reliable and template based approaches are less flexible to size and style variation of character font. We combine the positive aspects of feature based and template based approaches. Here we propose a run number based normalized template matching technique for compound character recognition. Run number vectors for both horizontal and vertical scanning are computed. As the number of scans may vary from pattern to pattern, we normalize and abbreviate the vector. We prove that this normalized and abbreviated vector induces metric distance. Moreover, this vector is invariant to scaling, insensitive to character style variation and more effective for more complex-shaped characters than simple-shaped ones. We use this vector representation for matching within a group of compound characters. We notice that the matching is more efficient if the vector is reorganized with respect to the centroid of the pattern. We have tested our approach on a large set of segmented compound characters at different point sizes as well as different styles. Italic characters are subject to preprocessing. The overall correct recognition rate is 99.69%.</div>
</front>
</TEI>
<affiliations><list><country><li>Inde</li>
</country>
<region><li>Bengale-Occidental</li>
</region>
<settlement><li>Calcutta</li>
</settlement>
<orgName><li>Institut indien de statistiques</li>
</orgName>
</list>
<tree><country name="Inde"><noRegion><name sortKey="Garain, U" sort="Garain, U" uniqKey="Garain U" first="U." last="Garain">U. Garain</name>
</noRegion>
<name sortKey="Chaudhuri, B B" sort="Chaudhuri, B B" uniqKey="Chaudhuri B" first="B. B." last="Chaudhuri">Bidyut Baran Chaudhuri</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 002316 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 002316 | 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:98-0385607 |texte= Compound character recognition by run number based metric distance }}
This area was generated with Dilib version V0.6.32. |