Effect of the perturbed correlation method for optical character recognition
Identifieur interne : 002422 ( Main/Exploration ); précédent : 002421; suivant : 002423Effect of the perturbed correlation method for optical character recognition
Auteurs : Michio Yasuda [Japon] ; Kazuhiko Yamamoto (informaticien) [Japon] ; Hiromitsu Yamada [Japon]Source :
- Pattern Recognition [ 0031-3203 ] ; 1996.
Abstract
In order to enhance the ability of correlation method in character recognition, we introduce the perturbation where all six parameters of a two-dimensional affine transformation are changed slightly from the original value, the correlation for all cases of the parameter set are tried, and the best correlation is taken as the final result. We used reciprocal directional features as the feature representation for the correlation, and it was applied to the handwritten Kanji character database ETL8b2. As a result of the experiment, the recognition accuracy was improved by 5%, and the maximum correct recognition rate was 97.4%. The problem to be solved is the enormous amount of computation that the procedure requires.
Url:
DOI: 10.1016/S0031-3203(96)00169-0
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000A77
- to stream Istex, to step Curation: 000A64
- to stream Istex, to step Checkpoint: 001872
- to stream Main, to step Merge: 002552
- to stream Main, to step Curation: 002422
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>Effect of the perturbed correlation method for optical character recognition</title><author><name sortKey="Yasuda, Michio" sort="Yasuda, Michio" uniqKey="Yasuda M" first="Michio" last="Yasuda">Michio Yasuda</name></author><author><name sortKey="Yamamoto, Kazuhiko" sort="Yamamoto, Kazuhiko" uniqKey="Yamamoto K" first="Kazuhiko" last="Yamamoto">Kazuhiko Yamamoto (informaticien)</name><affiliation><country>Japon</country><placeName><settlement type="city">Gifu (ville)</settlement><region type="province">Région du Chūbu</region><region type="prefecture">Préfecture de Gifu</region></placeName><orgName type="university" n="3">Université de Gifu</orgName></affiliation></author><author><name sortKey="Yamada, Hiromitsu" sort="Yamada, Hiromitsu" uniqKey="Yamada H" first="Hiromitsu" last="Yamada">Hiromitsu Yamada</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:BFFC19B23A954023A384EED41222ABBE62270047</idno><date when="1997" year="1997">1997</date><idno type="doi">10.1016/S0031-3203(96)00169-0</idno><idno type="url">https://api.istex.fr/document/BFFC19B23A954023A384EED41222ABBE62270047/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000A77</idno><idno type="wicri:Area/Istex/Curation">000A64</idno><idno type="wicri:Area/Istex/Checkpoint">001872</idno><idno type="wicri:doubleKey">0031-3203:1997:Yasuda M:effect:of:the</idno><idno type="wicri:Area/Main/Merge">002552</idno><idno type="wicri:Area/Main/Curation">002422</idno><idno type="wicri:Area/Main/Exploration">002422</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a">Effect of the perturbed correlation method for optical character recognition</title><author><name sortKey="Yasuda, Michio" sort="Yasuda, Michio" uniqKey="Yasuda M" first="Michio" last="Yasuda">Michio Yasuda</name><affiliation wicri:level="1"><country xml:lang="fr">Japon</country><wicri:regionArea>Department of Electronics and Information Science, Meisei University, Oume-shi, Tokyo 198</wicri:regionArea><placeName><settlement type="city">Tokyo</settlement></placeName></affiliation></author><author><name sortKey="Yamamoto, Kazuhiko" sort="Yamamoto, Kazuhiko" uniqKey="Yamamoto K" first="Kazuhiko" last="Yamamoto">Kazuhiko Yamamoto (informaticien)</name><affiliation wicri:level="4"><country xml:lang="fr">Japon</country><wicri:regionArea>Department of Electronics and Computer Engineering, Gifu University, Gifu 501-11</wicri:regionArea><orgName type="university">Université de Gifu</orgName><placeName><settlement type="city">Gifu (ville)</settlement><region type="province">Région du Chūbu</region><region type="prefecture">Préfecture de Gifu</region></placeName><placeName><settlement type="city">Gifu (ville)</settlement><region type="province">Région du Chūbu</region><region type="prefecture">Préfecture de Gifu</region></placeName><orgName type="university" n="3">Université de Gifu</orgName></affiliation></author><author><name sortKey="Yamada, Hiromitsu" sort="Yamada, Hiromitsu" uniqKey="Yamada H" first="Hiromitsu" last="Yamada">Hiromitsu Yamada</name><affiliation wicri:level="1"><country xml:lang="fr">Japon</country><wicri:regionArea>Electrotechnical Laboratory, Tsukuba, Ibaraki 305</wicri:regionArea><wicri:noRegion>Ibaraki 305</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="1315">1315</biblScope><biblScope unit="page" to="1320">1320</biblScope></imprint><idno type="ISSN">0031-3203</idno></series><idno type="istex">BFFC19B23A954023A384EED41222ABBE62270047</idno><idno type="DOI">10.1016/S0031-3203(96)00169-0</idno><idno type="PII">S0031-3203(96)00169-0</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">In order to enhance the ability of correlation method in character recognition, we introduce the perturbation where all six parameters of a two-dimensional affine transformation are changed slightly from the original value, the correlation for all cases of the parameter set are tried, and the best correlation is taken as the final result. We used reciprocal directional features as the feature representation for the correlation, and it was applied to the handwritten Kanji character database ETL8b2. As a result of the experiment, the recognition accuracy was improved by 5%, and the maximum correct recognition rate was 97.4%. The problem to be solved is the enormous amount of computation that the procedure requires.</div></front></TEI><affiliations><list><country><li>Japon</li></country><region><li>Préfecture de Gifu</li><li>Région du Chūbu</li></region><settlement><li>Gifu (ville)</li><li>Tokyo</li></settlement><orgName><li>Université de Gifu</li></orgName></list><tree><country name="Japon"><noRegion><name sortKey="Yasuda, Michio" sort="Yasuda, Michio" uniqKey="Yasuda M" first="Michio" last="Yasuda">Michio Yasuda</name></noRegion><name sortKey="Yamada, Hiromitsu" sort="Yamada, Hiromitsu" uniqKey="Yamada H" first="Hiromitsu" last="Yamada">Hiromitsu Yamada</name><name sortKey="Yamamoto, Kazuhiko" sort="Yamamoto, Kazuhiko" uniqKey="Yamamoto K" first="Kazuhiko" last="Yamamoto">Kazuhiko Yamamoto (informaticien)</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 002422 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 002422 | 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:BFFC19B23A954023A384EED41222ABBE62270047
|texte= Effect of the perturbed correlation method for optical character recognition
}}
| This area was generated with Dilib version V0.6.32. |  |