Highly accurate recognition of printed Korean characters through an improved two-stage classification method
Identifieur interne : 002004 ( Main/Merge ); précédent : 002003; suivant : 002005Highly accurate recognition of printed Korean characters through an improved two-stage classification method
Auteurs : Jin-Soo Lee [Corée du Sud] ; Oh-Jun Kwon [Corée du Sud] ; Sung-Yang Bang [Corée du Sud]Source :
- Pattern Recognition [ 0031-3203 ] ; 1996.
Abstract
This paper presents a recognition system which obtains a recognition rate higher than 99% for the printed Korean characters of multifont and multisize. We recognize a given input by first identifying the character type of the input and then recognizing its constituent graphemes. In order to improve the performance we incorporated three new ideas in our system: the expansion of the subimage areas used by the grapheme classifiers, an algorithm to accurately segment the horizontal vowel’s subimage areas, and a validation process to evaluate the result of the type classifier. Through experiments we confirmed that our system performs well in a multi-font and multi-size environment and that those three ideas actually contributed to improve the performance significantly.
Url:
DOI: 10.1016/S0031-3203(97)00126-X
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000960
- to stream Istex, to step Curation: 000950
- to stream Istex, to step Checkpoint: 001446
Links to Exploration step
ISTEX:03BF9890954450734AEBA0334C29CC34E79693E1Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>Highly accurate recognition of printed Korean characters through an improved two-stage classification method</title>
<author><name sortKey="Lee, Jin Soo" sort="Lee, Jin Soo" uniqKey="Lee J" first="Jin-Soo" last="Lee">Jin-Soo Lee</name>
</author>
<author><name sortKey="Kwon, Oh Jun" sort="Kwon, Oh Jun" uniqKey="Kwon O" first="Oh-Jun" last="Kwon">Oh-Jun Kwon</name>
</author>
<author><name sortKey="Bang, Sung Yang" sort="Bang, Sung Yang" uniqKey="Bang S" first="Sung-Yang" last="Bang">Sung-Yang Bang</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:03BF9890954450734AEBA0334C29CC34E79693E1</idno>
<date when="1999" year="1999">1999</date>
<idno type="doi">10.1016/S0031-3203(97)00126-X</idno>
<idno type="url">https://api.istex.fr/document/03BF9890954450734AEBA0334C29CC34E79693E1/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000960</idno>
<idno type="wicri:Area/Istex/Curation">000950</idno>
<idno type="wicri:Area/Istex/Checkpoint">001446</idno>
<idno type="wicri:doubleKey">0031-3203:1999:Lee J:highly:accurate:recognition</idno>
<idno type="wicri:Area/Main/Merge">002004</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a">Highly accurate recognition of printed Korean characters through an improved two-stage classification method</title>
<author><name sortKey="Lee, Jin Soo" sort="Lee, Jin Soo" uniqKey="Lee J" first="Jin-Soo" last="Lee">Jin-Soo Lee</name>
<affiliation wicri:level="1"><country xml:lang="fr">Corée du Sud</country>
<wicri:regionArea>MPC Gr., Multimedia Research Lab., LG Electronics Inc., 16 Woomyeon-dong, Seocho-gu, Seoul, 137-140</wicri:regionArea>
<wicri:noRegion>137-140</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Kwon, Oh Jun" sort="Kwon, Oh Jun" uniqKey="Kwon O" first="Oh-Jun" last="Kwon">Oh-Jun Kwon</name>
<affiliation wicri:level="1"><country xml:lang="fr">Corée du Sud</country>
<wicri:regionArea>Department of Computer Science & Engineering, Pohang University of Science and Technology, San 31 Hyoja-dong Pohang, 790-784</wicri:regionArea>
<wicri:noRegion>790-784</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Bang, Sung Yang" sort="Bang, Sung Yang" uniqKey="Bang S" first="Sung-Yang" last="Bang">Sung-Yang Bang</name>
<affiliation wicri:level="1"><country xml:lang="fr">Corée du Sud</country>
<wicri:regionArea>Department of Computer Science & Engineering, Pohang University of Science and Technology, San 31 Hyoja-dong Pohang, 790-784</wicri:regionArea>
<wicri:noRegion>790-784</wicri:noRegion>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="j">Pattern Recognition</title>
<title level="j" type="abbrev">PR</title>
<idno type="ISSN">0031-3203</idno>
<imprint><publisher>ELSEVIER</publisher>
<date type="published" when="1996">1996</date>
<biblScope unit="volume">32</biblScope>
<biblScope unit="issue">12</biblScope>
<biblScope unit="page" from="1935">1935</biblScope>
<biblScope unit="page" to="1945">1945</biblScope>
</imprint>
<idno type="ISSN">0031-3203</idno>
</series>
<idno type="istex">03BF9890954450734AEBA0334C29CC34E79693E1</idno>
<idno type="DOI">10.1016/S0031-3203(97)00126-X</idno>
<idno type="PII">S0031-3203(97)00126-X</idno>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0031-3203</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass></textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">This paper presents a recognition system which obtains a recognition rate higher than 99% for the printed Korean characters of multifont and multisize. We recognize a given input by first identifying the character type of the input and then recognizing its constituent graphemes. In order to improve the performance we incorporated three new ideas in our system: the expansion of the subimage areas used by the grapheme classifiers, an algorithm to accurately segment the horizontal vowel’s subimage areas, and a validation process to evaluate the result of the type classifier. Through experiments we confirmed that our system performs well in a multi-font and multi-size environment and that those three ideas actually contributed to improve the performance significantly.</div>
</front>
</TEI>
</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 002004 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 002004 | 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= ISTEX:03BF9890954450734AEBA0334C29CC34E79693E1 |texte= Highly accurate recognition of printed Korean characters through an improved two-stage classification method }}
This area was generated with Dilib version V0.6.32. |