Decision Tree Based Recognition of Bangla Text from Outdoor Scene Images
Identifieur interne : 000490 ( Main/Exploration ); précédent : 000489; suivant : 000491Decision Tree Based Recognition of Bangla Text from Outdoor Scene Images
Auteurs : Ranjit Ghoshal [Inde] ; Anandarup Roy [Inde] ; Kumar Bhowmik [Pays-Bas] ; K. Parui [Inde]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2011.
Abstract
Abstract: This article proposes a scheme for automatic recognition of Bangla text extracted from outdoor scene images. For extraction, we obtain the headline, then apply certain conditions to distinguish between text and non-text. By removing the headline we partition the text into two zones. We further observe an association among the text symbols in these two different zones. For recognition purpose, we design a decision tree classifier with Multilayer Perceptron (MLP) at leaf nodes. The root node takes into account all possible text symbols. Further nodes highlight distinguishable features and act as two-class classifiers. Finally, at leaf nodes, a few text symbols remain, that are recognized using MLP classifiers. The association between the two zones makes recognition simpler and efficient. The classifiers are trained using about 7100 samples of 52 classes. Experiments are performed on 250 images (200 scene images and 50 scanned images).
Url:
DOI: 10.1007/978-3-642-24965-5_61
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000C94
- to stream Istex, to step Curation: 000C71
- to stream Istex, to step Checkpoint: 000147
- to stream Main, to step Merge: 000496
- to stream Main, to step Curation: 000490
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Decision Tree Based Recognition of Bangla Text from Outdoor Scene Images</title>
<author><name sortKey="Ghoshal, Ranjit" sort="Ghoshal, Ranjit" uniqKey="Ghoshal R" first="Ranjit" last="Ghoshal">Ranjit Ghoshal</name>
</author>
<author><name sortKey="Roy, Anandarup" sort="Roy, Anandarup" uniqKey="Roy A" first="Anandarup" last="Roy">Anandarup Roy</name>
</author>
<author><name sortKey="Bhowmik, Kumar" sort="Bhowmik, Kumar" uniqKey="Bhowmik K" first="Kumar" last="Bhowmik">Kumar Bhowmik</name>
</author>
<author><name sortKey="Parui, K" sort="Parui, K" uniqKey="Parui K" first="K." last="Parui">K. Parui</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:D027B1CF07BE4D32CB491D95DFEE7A8DEB21D2D7</idno>
<date when="2011" year="2011">2011</date>
<idno type="doi">10.1007/978-3-642-24965-5_61</idno>
<idno type="url">https://api.istex.fr/document/D027B1CF07BE4D32CB491D95DFEE7A8DEB21D2D7/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000C94</idno>
<idno type="wicri:Area/Istex/Curation">000C71</idno>
<idno type="wicri:Area/Istex/Checkpoint">000147</idno>
<idno type="wicri:doubleKey">0302-9743:2011:Ghoshal R:decision:tree:based</idno>
<idno type="wicri:Area/Main/Merge">000496</idno>
<idno type="wicri:Area/Main/Curation">000490</idno>
<idno type="wicri:Area/Main/Exploration">000490</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Decision Tree Based Recognition of Bangla Text from Outdoor Scene Images</title>
<author><name sortKey="Ghoshal, Ranjit" sort="Ghoshal, Ranjit" uniqKey="Ghoshal R" first="Ranjit" last="Ghoshal">Ranjit Ghoshal</name>
<affiliation wicri:level="1"><country xml:lang="fr">Inde</country>
<wicri:regionArea>St. Thomas’ College of Engineering and Technology, 700023, Kolkata</wicri:regionArea>
<wicri:noRegion>Kolkata</wicri:noRegion>
</affiliation>
<affiliation><wicri:noCountry code="no comma">E-mail: ranjit.ghoshal@rediffmail.com</wicri:noCountry>
</affiliation>
</author>
<author><name sortKey="Roy, Anandarup" sort="Roy, Anandarup" uniqKey="Roy A" first="Anandarup" last="Roy">Anandarup Roy</name>
<affiliation wicri:level="1"><country xml:lang="fr">Inde</country>
<wicri:regionArea>CVPR Unit, Indian Statistical Institute</wicri:regionArea>
<wicri:noRegion>Indian Statistical Institute</wicri:noRegion>
</affiliation>
<affiliation><wicri:noCountry code="no comma">E-mail: roy.anandarup@gmail.com</wicri:noCountry>
</affiliation>
</author>
<author><name sortKey="Bhowmik, Kumar" sort="Bhowmik, Kumar" uniqKey="Bhowmik K" first="Kumar" last="Bhowmik">Kumar Bhowmik</name>
<affiliation wicri:level="4"><country xml:lang="fr">Pays-Bas</country>
<wicri:regionArea>Faculty of Mathematics and Natural Sciences, University of Groningen</wicri:regionArea>
<placeName><settlement type="city">Groningue (ville)</settlement>
<region>Groningue (province)</region>
</placeName>
<orgName type="university">Université de Groningue</orgName>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Pays-Bas</country>
</affiliation>
</author>
<author><name sortKey="Parui, K" sort="Parui, K" uniqKey="Parui K" first="K." last="Parui">K. Parui</name>
<affiliation wicri:level="1"><country xml:lang="fr">Inde</country>
<wicri:regionArea>CVPR Unit, Indian Statistical Institute</wicri:regionArea>
<wicri:noRegion>Indian Statistical Institute</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Inde</country>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="s">Lecture Notes in Computer Science</title>
<imprint><date>2011</date>
</imprint>
<idno type="ISSN">0302-9743</idno>
<idno type="eISSN">1611-3349</idno>
<idno type="ISSN">0302-9743</idno>
</series>
<idno type="istex">D027B1CF07BE4D32CB491D95DFEE7A8DEB21D2D7</idno>
<idno type="DOI">10.1007/978-3-642-24965-5_61</idno>
<idno type="ChapterID">61</idno>
<idno type="ChapterID">Chap61</idno>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0302-9743</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass></textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Abstract: This article proposes a scheme for automatic recognition of Bangla text extracted from outdoor scene images. For extraction, we obtain the headline, then apply certain conditions to distinguish between text and non-text. By removing the headline we partition the text into two zones. We further observe an association among the text symbols in these two different zones. For recognition purpose, we design a decision tree classifier with Multilayer Perceptron (MLP) at leaf nodes. The root node takes into account all possible text symbols. Further nodes highlight distinguishable features and act as two-class classifiers. Finally, at leaf nodes, a few text symbols remain, that are recognized using MLP classifiers. The association between the two zones makes recognition simpler and efficient. The classifiers are trained using about 7100 samples of 52 classes. Experiments are performed on 250 images (200 scene images and 50 scanned images).</div>
</front>
</TEI>
<affiliations><list><country><li>Inde</li>
<li>Pays-Bas</li>
</country>
<region><li>Groningue (province)</li>
</region>
<settlement><li>Groningue (ville)</li>
</settlement>
<orgName><li>Université de Groningue</li>
</orgName>
</list>
<tree><country name="Inde"><noRegion><name sortKey="Ghoshal, Ranjit" sort="Ghoshal, Ranjit" uniqKey="Ghoshal R" first="Ranjit" last="Ghoshal">Ranjit Ghoshal</name>
</noRegion>
<name sortKey="Parui, K" sort="Parui, K" uniqKey="Parui K" first="K." last="Parui">K. Parui</name>
<name sortKey="Parui, K" sort="Parui, K" uniqKey="Parui K" first="K." last="Parui">K. Parui</name>
<name sortKey="Roy, Anandarup" sort="Roy, Anandarup" uniqKey="Roy A" first="Anandarup" last="Roy">Anandarup Roy</name>
</country>
<country name="Pays-Bas"><region name="Groningue (province)"><name sortKey="Bhowmik, Kumar" sort="Bhowmik, Kumar" uniqKey="Bhowmik K" first="Kumar" last="Bhowmik">Kumar Bhowmik</name>
</region>
<name sortKey="Bhowmik, Kumar" sort="Bhowmik, Kumar" uniqKey="Bhowmik K" first="Kumar" last="Bhowmik">Kumar Bhowmik</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 000490 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000490 | 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:D027B1CF07BE4D32CB491D95DFEE7A8DEB21D2D7 |texte= Decision Tree Based Recognition of Bangla Text from Outdoor Scene Images }}
This area was generated with Dilib version V0.6.32. |