Multi-level post-processing for Korean character recognition using morphological analysis and linguistic evaluation
Identifieur interne : 002521 ( Main/Merge ); précédent : 002520; suivant : 002522Multi-level post-processing for Korean character recognition using morphological analysis and linguistic evaluation
Auteurs : Geunbae Lee [Corée du Sud] ; Jong-Hyeok Lee [Corée du Sud] ; Jinhee Yoo [Corée du Sud]Source :
- Pattern Recognition [ 0031-3203 ] ; 1996.
Abstract
Most of the post-processing methods for character recognition rely on contextual information of character and word-fragment levels. However, due to linguistic characteristics of Korean, such low-level information alone is not sufficient for high-quality character-recognition applications, and we need much higher-level contextual information to improve the recognition results. This paper presents a domain independent post-processing technique that utilizes multi-level morphological, syntactic, and semantic information as well as character-level information. The proposed post-processing system performs three-level processing: candidate character-set selection, candidate eojeol (Korean word) generation through morphological analysis, and final single eojeol-sequence selection by linguistic evaluation. All the required linguistic information and probabilities are automatically acquired from a statistical corpus analysis. Experimental results demonstrate the effectiveness of our method, yielding an error correction rate of 80.46%, and improved recognition rate of 95.53% from the before-post-processing rate of 71.2% for single best-solution selection.
Url:
DOI: 10.1016/S0031-3203(96)00156-2
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 001B83
- to stream Istex, to step Curation: 001A71
- to stream Istex, to step Checkpoint: 001841
Links to Exploration step
ISTEX:5BF85BB14132147049C6E647BFE729A97CE7CF10Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>Multi-level post-processing for Korean character recognition using morphological analysis and linguistic evaluation</title><author><name sortKey="Lee, Geunbae" sort="Lee, Geunbae" uniqKey="Lee G" first="Geunbae" last="Lee">Geunbae Lee</name></author><author><name sortKey="Lee, Jong Hyeok" sort="Lee, Jong Hyeok" uniqKey="Lee J" first="Jong-Hyeok" last="Lee">Jong-Hyeok Lee</name></author><author><name sortKey="Yoo, Jinhee" sort="Yoo, Jinhee" uniqKey="Yoo J" first="Jinhee" last="Yoo">Jinhee Yoo</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:5BF85BB14132147049C6E647BFE729A97CE7CF10</idno><date when="1997" year="1997">1997</date><idno type="doi">10.1016/S0031-3203(96)00156-2</idno><idno type="url">https://api.istex.fr/document/5BF85BB14132147049C6E647BFE729A97CE7CF10/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">001B83</idno><idno type="wicri:Area/Istex/Curation">001A71</idno><idno type="wicri:Area/Istex/Checkpoint">001841</idno><idno type="wicri:doubleKey">0031-3203:1997:Lee G:multi:level:post</idno><idno type="wicri:Area/Main/Merge">002521</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a">Multi-level post-processing for Korean character recognition using morphological analysis and linguistic evaluation</title><author><name sortKey="Lee, Geunbae" sort="Lee, Geunbae" uniqKey="Lee G" first="Geunbae" last="Lee">Geunbae Lee</name><affiliation wicri:level="1"><country xml:lang="fr">Corée du Sud</country><wicri:regionArea>Department of Computer Science and Engineering, Pohang University of Science and Technology, San 31, Hoja-Dong, Pohang 790-784</wicri:regionArea><wicri:noRegion>Pohang 790-784</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Corée du Sud</country></affiliation></author><author><name sortKey="Lee, Jong Hyeok" sort="Lee, Jong Hyeok" uniqKey="Lee J" first="Jong-Hyeok" last="Lee">Jong-Hyeok Lee</name><affiliation wicri:level="1"><country xml:lang="fr">Corée du Sud</country><wicri:regionArea>Department of Computer Science and Engineering, Pohang University of Science and Technology, San 31, Hoja-Dong, Pohang 790-784</wicri:regionArea><wicri:noRegion>Pohang 790-784</wicri:noRegion></affiliation></author><author><name sortKey="Yoo, Jinhee" sort="Yoo, Jinhee" uniqKey="Yoo J" first="Jinhee" last="Yoo">Jinhee Yoo</name><affiliation wicri:level="1"><country xml:lang="fr">Corée du Sud</country><wicri:regionArea>Department of Computer Science and Engineering, Pohang University of Science and Technology, San 31, Hoja-Dong, Pohang 790-784</wicri:regionArea><wicri:noRegion>Pohang 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">30</biblScope><biblScope unit="issue">8</biblScope><biblScope unit="page" from="1347">1347</biblScope><biblScope unit="page" to="1360">1360</biblScope></imprint><idno type="ISSN">0031-3203</idno></series><idno type="istex">5BF85BB14132147049C6E647BFE729A97CE7CF10</idno><idno type="DOI">10.1016/S0031-3203(96)00156-2</idno><idno type="PII">S0031-3203(96)00156-2</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">Most of the post-processing methods for character recognition rely on contextual information of character and word-fragment levels. However, due to linguistic characteristics of Korean, such low-level information alone is not sufficient for high-quality character-recognition applications, and we need much higher-level contextual information to improve the recognition results. This paper presents a domain independent post-processing technique that utilizes multi-level morphological, syntactic, and semantic information as well as character-level information. The proposed post-processing system performs three-level processing: candidate character-set selection, candidate eojeol (Korean word) generation through morphological analysis, and final single eojeol-sequence selection by linguistic evaluation. All the required linguistic information and probabilities are automatically acquired from a statistical corpus analysis. Experimental results demonstrate the effectiveness of our method, yielding an error correction rate of 80.46%, and improved recognition rate of 95.53% from the before-post-processing rate of 71.2% for single best-solution selection.</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 002521 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 002521 | 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:5BF85BB14132147049C6E647BFE729A97CE7CF10
|texte= Multi-level post-processing for Korean character recognition using morphological analysis and linguistic evaluation
}}
| This area was generated with Dilib version V0.6.32. |  |