Word–Wise Script Identification from Indian Documents
Identifieur interne : 001458 ( Main/Exploration ); précédent : 001457; suivant : 001459Word–Wise Script Identification from Indian Documents
Auteurs : Suranjit Sinha [Inde] ; Umapada Pal [Inde] ; Bidyut Baran Chaudhuri [Inde]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2004.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
Abstract: In a country like India, a single text line of most of the official documents contains two different script words. Under two-language formula, the Indian documents are written in English and the state official language. For Optical Character Recognition (OCR) of such a document page, it is necessary to separate different script words before feeding them to the OCRs of individual scripts. In this paper a robust technique is proposed to extract word-wise script identification from Indian doublet form documents. Here, at first, the document is segmented into lines and then the lines are segmented into words. Using different topological and structural features (like number of loops, headline feature, water reservoir concept based features, profile features, etc.) individual script words are identified from the documents. The proposed scheme is tested on 24210 words of different doublets and we received more than 97% accuracy, on average.
Url:
DOI: 10.1007/978-3-540-28640-0_29
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000498
- to stream Istex, to step Curation: 000491
- to stream Istex, to step Checkpoint: 000C93
- to stream Main, to step Merge: 001509
- to stream PascalFrancis, to step Corpus: 000521
- to stream PascalFrancis, to step Curation: 000268
- to stream PascalFrancis, to step Checkpoint: 000446
- to stream Main, to step Merge: 001657
- to stream Main, to step Curation: 001458
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Word–Wise Script Identification from Indian Documents</title>
<author><name sortKey="Sinha, Suranjit" sort="Sinha, Suranjit" uniqKey="Sinha S" first="Suranjit" last="Sinha">Suranjit Sinha</name>
</author>
<author><name sortKey="Pal, Umapada" sort="Pal, Umapada" uniqKey="Pal U" first="Umapada" last="Pal">Umapada Pal</name>
</author>
<author><name sortKey="Chaudhuri, B" sort="Chaudhuri, B" uniqKey="Chaudhuri B" first="B." last="Chaudhuri">Bidyut Baran Chaudhuri</name>
<affiliation><country>Inde</country>
<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">ISTEX</idno>
<idno type="RBID">ISTEX:DF8BFCAE28D0DD31D95FD2F67000772E8B8DB97E</idno>
<date when="2004" year="2004">2004</date>
<idno type="doi">10.1007/978-3-540-28640-0_29</idno>
<idno type="url">https://api.istex.fr/document/DF8BFCAE28D0DD31D95FD2F67000772E8B8DB97E/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000498</idno>
<idno type="wicri:Area/Istex/Curation">000491</idno>
<idno type="wicri:Area/Istex/Checkpoint">000C93</idno>
<idno type="wicri:doubleKey">0302-9743:2004:Sinha S:word:wise:script</idno>
<idno type="wicri:Area/Main/Merge">001509</idno>
<idno type="wicri:source">INIST</idno>
<idno type="RBID">Pascal:04-0533877</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000521</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000268</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000446</idno>
<idno type="wicri:doubleKey">0302-9743:2004:Sinha S:word:wise:script</idno>
<idno type="wicri:Area/Main/Merge">001657</idno>
<idno type="wicri:Area/Main/Curation">001458</idno>
<idno type="wicri:Area/Main/Exploration">001458</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Word–Wise Script Identification from Indian Documents</title>
<author><name sortKey="Sinha, Suranjit" sort="Sinha, Suranjit" uniqKey="Sinha S" first="Suranjit" last="Sinha">Suranjit Sinha</name>
<affiliation wicri:level="1"><country xml:lang="fr">Inde</country>
<wicri:regionArea>Computer Vision and Pattern Recognition Unit, Indian Statistical Unit, 203 B.T. Road, 700 108, Kolkata</wicri:regionArea>
<wicri:noRegion>Kolkata</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Pal, Umapada" sort="Pal, Umapada" uniqKey="Pal U" first="Umapada" last="Pal">Umapada Pal</name>
<affiliation wicri:level="1"><country xml:lang="fr">Inde</country>
<wicri:regionArea>Computer Vision and Pattern Recognition Unit, Indian Statistical Unit, 203 B.T. Road, 700 108, Kolkata</wicri:regionArea>
<wicri:noRegion>Kolkata</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Inde</country>
</affiliation>
</author>
<author><name sortKey="Chaudhuri, B" sort="Chaudhuri, B" uniqKey="Chaudhuri B" first="B." last="Chaudhuri">Bidyut Baran Chaudhuri</name>
<affiliation wicri:level="1"><country xml:lang="fr">Inde</country>
<wicri:regionArea>Computer Vision and Pattern Recognition Unit, Indian Statistical Unit, 203 B.T. Road, 700 108, Kolkata</wicri:regionArea>
<wicri:noRegion>Kolkata</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>
<monogr></monogr>
<series><title level="s">Lecture Notes in Computer Science</title>
<imprint><date>2004</date>
</imprint>
<idno type="ISSN">0302-9743</idno>
<idno type="eISSN">1611-3349</idno>
<idno type="ISSN">0302-9743</idno>
</series>
<idno type="istex">DF8BFCAE28D0DD31D95FD2F67000772E8B8DB97E</idno>
<idno type="DOI">10.1007/978-3-540-28640-0_29</idno>
<idno type="ChapterID">29</idno>
<idno type="ChapterID">Chap29</idno>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0302-9743</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Character recognition</term>
<term>Data analysis</term>
<term>Document structure</term>
<term>Line segment</term>
<term>Optical character recognition</term>
<term>Text</term>
<term>Topology</term>
<term>Written communication</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Analyse donnée</term>
<term>Communication écrite</term>
<term>Reconnaissance caractère</term>
<term>Reconnaissance optique caractère</term>
<term>Segment droite</term>
<term>Structure document</term>
<term>Texte</term>
<term>Topologie</term>
</keywords>
</textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Abstract: In a country like India, a single text line of most of the official documents contains two different script words. Under two-language formula, the Indian documents are written in English and the state official language. For Optical Character Recognition (OCR) of such a document page, it is necessary to separate different script words before feeding them to the OCRs of individual scripts. In this paper a robust technique is proposed to extract word-wise script identification from Indian doublet form documents. Here, at first, the document is segmented into lines and then the lines are segmented into words. Using different topological and structural features (like number of loops, headline feature, water reservoir concept based features, profile features, etc.) individual script words are identified from the documents. The proposed scheme is tested on 24210 words of different doublets and we received more than 97% accuracy, on average.</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="Sinha, Suranjit" sort="Sinha, Suranjit" uniqKey="Sinha S" first="Suranjit" last="Sinha">Suranjit Sinha</name>
</noRegion>
<name sortKey="Chaudhuri, B" sort="Chaudhuri, B" uniqKey="Chaudhuri B" first="B." last="Chaudhuri">Bidyut Baran Chaudhuri</name>
<name sortKey="Pal, Umapada" sort="Pal, Umapada" uniqKey="Pal U" first="Umapada" last="Pal">Umapada Pal</name>
<name sortKey="Pal, Umapada" sort="Pal, Umapada" uniqKey="Pal U" first="Umapada" last="Pal">Umapada Pal</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 001458 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001458 | 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= ISTEX:DF8BFCAE28D0DD31D95FD2F67000772E8B8DB97E |texte= Word–Wise Script Identification from Indian Documents }}
This area was generated with Dilib version V0.6.32. |