Offline Isolated Handwritten Thai OCR Using Island-Based Projection with N-Gram Models and Hidden Markov Models
Identifieur interne : 001876 ( Main/Exploration ); précédent : 001875; suivant : 001877Offline Isolated Handwritten Thai OCR Using Island-Based Projection with N-Gram Models and Hidden Markov Models
Auteurs : Thanaruk Theeramunkong [Thaïlande] ; Chainat Wongtapan [Thaïlande] ; Sukree Sinthupinyo [Thaïlande]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2002.
Descripteurs français
- Pascal (Inist)
- Wicri :
- geographic : Thaïlande.
English descriptors
- KwdEn :
Abstract
Abstract: Many traditional works on offline Thai handwritten character recognition use a set of local features including circles, concavity, endpoints and lines to recognize hand-printed characters. However, in natural handwriting, these local features are often missed due to fast writing, resulting in dramatically reduced recognition accuracy. Instead of using such local features, this paper presents a method to extract features from handwritten characters using so-called multi-directional island-based projection. Two statistical recognition approaches using interpolated n-gram model (n-gram) and hidden Markov model (HMM) are also proposed. The performance of our feature extraction and recognition methods is investigated using nearly 23,400 hand-printed and natural-written characters, collected from 25 subjects. The results showed that, in situations where local features are hard to detect, both n-gram and HMM approaches achieved up to 96–99 % accuracy for close tests and 84–90 % for open tests.
Url:
DOI: 10.1007/3-540-36227-4_39
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000184
- to stream Istex, to step Curation: 000181
- to stream Istex, to step Checkpoint: 000F90
- to stream Main, to step Merge: 001956
- to stream PascalFrancis, to step Corpus: 000630
- to stream PascalFrancis, to step Curation: 000161
- to stream PascalFrancis, to step Checkpoint: 000603
- to stream Main, to step Merge: 001A56
- to stream Main, to step Curation: 001876
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Offline Isolated Handwritten Thai OCR Using Island-Based Projection with N-Gram Models and Hidden Markov Models</title>
<author><name sortKey="Theeramunkong, Thanaruk" sort="Theeramunkong, Thanaruk" uniqKey="Theeramunkong T" first="Thanaruk" last="Theeramunkong">Thanaruk Theeramunkong</name>
</author>
<author><name sortKey="Wongtapan, Chainat" sort="Wongtapan, Chainat" uniqKey="Wongtapan C" first="Chainat" last="Wongtapan">Chainat Wongtapan</name>
</author>
<author><name sortKey="Sinthupinyo, Sukree" sort="Sinthupinyo, Sukree" uniqKey="Sinthupinyo S" first="Sukree" last="Sinthupinyo">Sukree Sinthupinyo</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:1E6B19E5E273920E673BDAE1227443A27CD89A52</idno>
<date when="2002" year="2002">2002</date>
<idno type="doi">10.1007/3-540-36227-4_39</idno>
<idno type="url">https://api.istex.fr/document/1E6B19E5E273920E673BDAE1227443A27CD89A52/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000184</idno>
<idno type="wicri:Area/Istex/Curation">000181</idno>
<idno type="wicri:Area/Istex/Checkpoint">000F90</idno>
<idno type="wicri:doubleKey">0302-9743:2002:Theeramunkong T:offline:isolated:handwritten</idno>
<idno type="wicri:Area/Main/Merge">001956</idno>
<idno type="wicri:source">INIST</idno>
<idno type="RBID">Pascal:03-0142338</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000630</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000161</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000603</idno>
<idno type="wicri:doubleKey">0302-9743:2002:Theeramunkong T:offline:isolated:handwritten</idno>
<idno type="wicri:Area/Main/Merge">001A56</idno>
<idno type="wicri:Area/Main/Curation">001876</idno>
<idno type="wicri:Area/Main/Exploration">001876</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Offline Isolated Handwritten Thai OCR Using Island-Based Projection with N-Gram Models and Hidden Markov Models</title>
<author><name sortKey="Theeramunkong, Thanaruk" sort="Theeramunkong, Thanaruk" uniqKey="Theeramunkong T" first="Thanaruk" last="Theeramunkong">Thanaruk Theeramunkong</name>
<affiliation wicri:level="1"><country xml:lang="fr">Thaïlande</country>
<wicri:regionArea>Information Technology Program Sirindhorn International Institute of Technology, Thammasat University, Thammasat Rangsit Post Office, PO. BOX. 22, 12121, Pathumthani</wicri:regionArea>
<wicri:noRegion>Pathumthani</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Thaïlande</country>
</affiliation>
</author>
<author><name sortKey="Wongtapan, Chainat" sort="Wongtapan, Chainat" uniqKey="Wongtapan C" first="Chainat" last="Wongtapan">Chainat Wongtapan</name>
<affiliation wicri:level="1"><country xml:lang="fr">Thaïlande</country>
<wicri:regionArea>Computer Science and Technology Faculty, Thammasat University, 12121, Pathumthani</wicri:regionArea>
<wicri:noRegion>Pathumthani</wicri:noRegion>
</affiliation>
<affiliation><wicri:noCountry code="no comma">E-mail: chainat@hotmail.com</wicri:noCountry>
</affiliation>
</author>
<author><name sortKey="Sinthupinyo, Sukree" sort="Sinthupinyo, Sukree" uniqKey="Sinthupinyo S" first="Sukree" last="Sinthupinyo">Sukree Sinthupinyo</name>
<affiliation wicri:level="1"><country xml:lang="fr">Thaïlande</country>
<wicri:regionArea>Computer Science and Technology Faculty, Thammasat University, 12121, Pathumthani</wicri:regionArea>
<wicri:noRegion>Pathumthani</wicri:noRegion>
</affiliation>
<affiliation><wicri:noCountry code="no comma">E-mail: sukree@hotmail.com</wicri:noCountry>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="s">Lecture Notes in Computer Science</title>
<imprint><date>2002</date>
</imprint>
<idno type="ISSN">0302-9743</idno>
<idno type="ISSN">0302-9743</idno>
</series>
<idno type="istex">1E6B19E5E273920E673BDAE1227443A27CD89A52</idno>
<idno type="DOI">10.1007/3-540-36227-4_39</idno>
<idno type="ChapterID">39</idno>
<idno type="ChapterID">Chap39</idno>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0302-9743</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Hidden Markov model</term>
<term>Manuscript character</term>
<term>Method</term>
<term>Models</term>
<term>Optical character recognition</term>
<term>Oriental language</term>
<term>Pattern extraction</term>
<term>Thailand</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Caractère manuscrit</term>
<term>Extraction forme</term>
<term>Langue orientale</term>
<term>Modèle</term>
<term>Modèle Markov caché</term>
<term>Méthode</term>
<term>Reconnaissance optique caractère</term>
<term>Thaïlande</term>
</keywords>
<keywords scheme="Wicri" type="geographic" xml:lang="fr"><term>Thaïlande</term>
</keywords>
</textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Abstract: Many traditional works on offline Thai handwritten character recognition use a set of local features including circles, concavity, endpoints and lines to recognize hand-printed characters. However, in natural handwriting, these local features are often missed due to fast writing, resulting in dramatically reduced recognition accuracy. Instead of using such local features, this paper presents a method to extract features from handwritten characters using so-called multi-directional island-based projection. Two statistical recognition approaches using interpolated n-gram model (n-gram) and hidden Markov model (HMM) are also proposed. The performance of our feature extraction and recognition methods is investigated using nearly 23,400 hand-printed and natural-written characters, collected from 25 subjects. The results showed that, in situations where local features are hard to detect, both n-gram and HMM approaches achieved up to 96–99 % accuracy for close tests and 84–90 % for open tests.</div>
</front>
</TEI>
<affiliations><list><country><li>Thaïlande</li>
</country>
</list>
<tree><country name="Thaïlande"><noRegion><name sortKey="Theeramunkong, Thanaruk" sort="Theeramunkong, Thanaruk" uniqKey="Theeramunkong T" first="Thanaruk" last="Theeramunkong">Thanaruk Theeramunkong</name>
</noRegion>
<name sortKey="Sinthupinyo, Sukree" sort="Sinthupinyo, Sukree" uniqKey="Sinthupinyo S" first="Sukree" last="Sinthupinyo">Sukree Sinthupinyo</name>
<name sortKey="Theeramunkong, Thanaruk" sort="Theeramunkong, Thanaruk" uniqKey="Theeramunkong T" first="Thanaruk" last="Theeramunkong">Thanaruk Theeramunkong</name>
<name sortKey="Wongtapan, Chainat" sort="Wongtapan, Chainat" uniqKey="Wongtapan C" first="Chainat" last="Wongtapan">Chainat Wongtapan</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 001876 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001876 | 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:1E6B19E5E273920E673BDAE1227443A27CD89A52 |texte= Offline Isolated Handwritten Thai OCR Using Island-Based Projection with N-Gram Models and Hidden Markov Models }}
This area was generated with Dilib version V0.6.32. |