Robust feature extraction method based on run‐length compensation for degraded character recognition
Identifieur interne : 001486 ( Main/Exploration ); précédent : 001485; suivant : 001487Robust feature extraction method based on run‐length compensation for degraded character recognition
Auteurs : Minoru Mori [Japon] ; Minako Sawaki [Japon] ; Norihiro Hagita [Japon] ; Hiroshi Murase [Japon] ; Naoki Mukawa [Japon]Source :
- Systems and Computers in Japan [ 0882-1666 ] ; 2004-08.
English descriptors
- KwdEn :
Abstract
Conventional features are robust for recognizing either deformed or degraded characters. Most conventional character recognition methods address either one or the other. This paper proposes a feature extraction method that is robust for both of them. Run‐length compensation is introduced for approximately extracting directional run‐lengths of strokes from degraded handwritten characters. This technique is applied to the conventional feature vector based on directional run‐lengths. Experiments for handwritten characters with additive or subtractive noise show that the proposed feature is superior to conventional ones over a wide range of the degree of noise. © 2004 Wiley Periodicals, Inc. Syst Comp Jpn, 35(9): 1–9, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.10643
Url:
DOI: 10.1002/scj.10643
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 002127
- to stream Istex, to step Curation: 001F85
- to stream Istex, to step Checkpoint: 000D21
- to stream Main, to step Merge: 001537
- to stream Main, to step Curation: 001486
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Robust feature extraction method based on run‐length compensation for degraded character recognition</title><author><name sortKey="Mori, Minoru" sort="Mori, Minoru" uniqKey="Mori M" first="Minoru" last="Mori">Minoru Mori</name></author><author><name sortKey="Sawaki, Minako" sort="Sawaki, Minako" uniqKey="Sawaki M" first="Minako" last="Sawaki">Minako Sawaki</name></author><author><name sortKey="Hagita, Norihiro" sort="Hagita, Norihiro" uniqKey="Hagita N" first="Norihiro" last="Hagita">Norihiro Hagita</name></author><author><name sortKey="Murase, Hiroshi" sort="Murase, Hiroshi" uniqKey="Murase H" first="Hiroshi" last="Murase">Hiroshi Murase</name></author><author><name sortKey="Mukawa, Naoki" sort="Mukawa, Naoki" uniqKey="Mukawa N" first="Naoki" last="Mukawa">Naoki Mukawa</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:E53E90C5F7A5779A2CBB17977B61AFCC92B39DD9</idno><date when="2004" year="2004">2004</date><idno type="doi">10.1002/scj.10643</idno><idno type="url">https://api.istex.fr/document/E53E90C5F7A5779A2CBB17977B61AFCC92B39DD9/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">002127</idno><idno type="wicri:Area/Istex/Curation">001F85</idno><idno type="wicri:Area/Istex/Checkpoint">000D21</idno><idno type="wicri:doubleKey">0882-1666:2004:Mori M:robust:feature:extraction</idno><idno type="wicri:Area/Main/Merge">001537</idno><idno type="wicri:Area/Main/Curation">001486</idno><idno type="wicri:Area/Main/Exploration">001486</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Robust feature extraction method based on run‐length compensation for degraded character recognition</title><author><name sortKey="Mori, Minoru" sort="Mori, Minoru" uniqKey="Mori M" first="Minoru" last="Mori">Minoru Mori</name><affiliation wicri:level="1"><country xml:lang="fr">Japon</country><wicri:regionArea>NTT Communication Science Laboratories, NTT Corporation, Atsugi</wicri:regionArea><wicri:noRegion>Atsugi</wicri:noRegion></affiliation></author><author><name sortKey="Sawaki, Minako" sort="Sawaki, Minako" uniqKey="Sawaki M" first="Minako" last="Sawaki">Minako Sawaki</name><affiliation wicri:level="1"><country xml:lang="fr">Japon</country><wicri:regionArea>NTT Communication Science Laboratories, NTT Corporation, Atsugi</wicri:regionArea><wicri:noRegion>Atsugi</wicri:noRegion></affiliation></author><author><name sortKey="Hagita, Norihiro" sort="Hagita, Norihiro" uniqKey="Hagita N" first="Norihiro" last="Hagita">Norihiro Hagita</name><affiliation wicri:level="1"><country xml:lang="fr">Japon</country><wicri:regionArea>NTT Communication Science Laboratories, NTT Corporation, Atsugi</wicri:regionArea><wicri:noRegion>Atsugi</wicri:noRegion></affiliation></author><author><name sortKey="Murase, Hiroshi" sort="Murase, Hiroshi" uniqKey="Murase H" first="Hiroshi" last="Murase">Hiroshi Murase</name><affiliation wicri:level="1"><country xml:lang="fr">Japon</country><wicri:regionArea>NTT Communication Science Laboratories, NTT Corporation, Atsugi</wicri:regionArea><wicri:noRegion>Atsugi</wicri:noRegion></affiliation></author><author><name sortKey="Mukawa, Naoki" sort="Mukawa, Naoki" uniqKey="Mukawa N" first="Naoki" last="Mukawa">Naoki Mukawa</name><affiliation wicri:level="1"><country xml:lang="fr">Japon</country><wicri:regionArea>NTT Communication Science Laboratories, NTT Corporation, Atsugi</wicri:regionArea><wicri:noRegion>Atsugi</wicri:noRegion></affiliation></author></analytic><monogr></monogr><series><title level="j">Systems and Computers in Japan</title><title level="j" type="abbrev">Syst. Comp. Jpn.</title><idno type="ISSN">0882-1666</idno><idno type="eISSN">1520-684X</idno><imprint><publisher>Wiley Subscription Services, Inc., A Wiley Company</publisher><pubPlace>Hoboken</pubPlace><date type="published" when="2004-08">2004-08</date><biblScope unit="volume">35</biblScope><biblScope unit="issue">9</biblScope><biblScope unit="page" from="1">1</biblScope><biblScope unit="page" to="9">9</biblScope></imprint><idno type="ISSN">0882-1666</idno></series><idno type="istex">E53E90C5F7A5779A2CBB17977B61AFCC92B39DD9</idno><idno type="DOI">10.1002/scj.10643</idno><idno type="ArticleID">SCJ10643</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0882-1666</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>OCR</term><term>degradation estimation</term><term>direction contributivity</term><term>feature extraction</term><term>run‐length compensation</term></keywords></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Conventional features are robust for recognizing either deformed or degraded characters. Most conventional character recognition methods address either one or the other. This paper proposes a feature extraction method that is robust for both of them. Run‐length compensation is introduced for approximately extracting directional run‐lengths of strokes from degraded handwritten characters. This technique is applied to the conventional feature vector based on directional run‐lengths. Experiments for handwritten characters with additive or subtractive noise show that the proposed feature is superior to conventional ones over a wide range of the degree of noise. © 2004 Wiley Periodicals, Inc. Syst Comp Jpn, 35(9): 1–9, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.10643</div></front></TEI><affiliations><list><country><li>Japon</li></country></list><tree><country name="Japon"><noRegion><name sortKey="Mori, Minoru" sort="Mori, Minoru" uniqKey="Mori M" first="Minoru" last="Mori">Minoru Mori</name></noRegion><name sortKey="Hagita, Norihiro" sort="Hagita, Norihiro" uniqKey="Hagita N" first="Norihiro" last="Hagita">Norihiro Hagita</name><name sortKey="Mukawa, Naoki" sort="Mukawa, Naoki" uniqKey="Mukawa N" first="Naoki" last="Mukawa">Naoki Mukawa</name><name sortKey="Murase, Hiroshi" sort="Murase, Hiroshi" uniqKey="Murase H" first="Hiroshi" last="Murase">Hiroshi Murase</name><name sortKey="Sawaki, Minako" sort="Sawaki, Minako" uniqKey="Sawaki M" first="Minako" last="Sawaki">Minako Sawaki</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 001486 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001486 | 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:E53E90C5F7A5779A2CBB17977B61AFCC92B39DD9
|texte= Robust feature extraction method based on run‐length compensation for degraded character recognition
}}
| This area was generated with Dilib version V0.6.32. |  |