Video text recognition using category‐dependent feature extraction based on feature compensation
Identifieur interne : 001228 ( Main/Exploration ); précédent : 001227; suivant : 001229Video text recognition using category‐dependent feature extraction based on feature compensation
Auteurs : Minoru Mori [Japon] ; Minako Sawaki [Japon] ; Norihiro Hagita [Japon]Source :
- Systems and Computers in Japan [ 0882-1666 ] ; 2005-09.
English descriptors
Abstract
When recognizing multiple fonts, geometric features, such as the directional information of strokes, are generally robust against deformation but are weak against degradation. This paper describes a category‐dependent feature extraction method that uses feature compensation to overcome this weakness. Our proposed method estimates the degree of degradation of an input pattern by comparing the input pattern to a template of each category. This estimation enables us to offset the degradation in feature values. We apply the proposed method to the recognition of video text suffering from both degradation and deformation. Recognition experiments using characters extracted from videos show that the proposed method is superior to the conventional alternatives in resisting degradation. © 2005 Wiley Periodicals, Inc. Syst Comp Jpn, 36(10): 1–8, 2005; Published online in Wiley InterScience (www.interscience. wiley.com). DOI 10.1002/scj.20361
Url:
DOI: 10.1002/scj.20361
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 001071
- to stream Istex, to step Curation: 001018
- to stream Istex, to step Checkpoint: 000B37
- to stream Main, to step Merge: 001264
- to stream Main, to step Curation: 001228
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Video text recognition using category‐dependent feature extraction based on feature compensation</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></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:8B8AF82F6B7BBDBE581083A574D358ACBA40023A</idno><date when="2005" year="2005">2005</date><idno type="doi">10.1002/scj.20361</idno><idno type="url">https://api.istex.fr/document/8B8AF82F6B7BBDBE581083A574D358ACBA40023A/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">001071</idno><idno type="wicri:Area/Istex/Curation">001018</idno><idno type="wicri:Area/Istex/Checkpoint">000B37</idno><idno type="wicri:doubleKey">0882-1666:2005:Mori M:video:text:recognition</idno><idno type="wicri:Area/Main/Merge">001264</idno><idno type="wicri:Area/Main/Curation">001228</idno><idno type="wicri:Area/Main/Exploration">001228</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Video text recognition using category‐dependent feature extraction based on feature compensation</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 Science and Core Technology Laboratory Group, 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>ATR Intelligent Robotics and Communication Laboratories, Keihanna Science City</wicri:regionArea><wicri:noRegion>Keihanna Science City</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="2005-09">2005-09</date><biblScope unit="volume">36</biblScope><biblScope unit="issue">10</biblScope><biblScope unit="page" from="1">1</biblScope><biblScope unit="page" to="8">8</biblScope></imprint><idno type="ISSN">0882-1666</idno></series><idno type="istex">8B8AF82F6B7BBDBE581083A574D358ACBA40023A</idno><idno type="DOI">10.1002/scj.20361</idno><idno type="ArticleID">SCJ20361</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0882-1666</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>OCR</term><term>category‐dependent</term><term>compensation</term><term>deformation</term><term>degradation</term><term>feature extraction</term></keywords></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">When recognizing multiple fonts, geometric features, such as the directional information of strokes, are generally robust against deformation but are weak against degradation. This paper describes a category‐dependent feature extraction method that uses feature compensation to overcome this weakness. Our proposed method estimates the degree of degradation of an input pattern by comparing the input pattern to a template of each category. This estimation enables us to offset the degradation in feature values. We apply the proposed method to the recognition of video text suffering from both degradation and deformation. Recognition experiments using characters extracted from videos show that the proposed method is superior to the conventional alternatives in resisting degradation. © 2005 Wiley Periodicals, Inc. Syst Comp Jpn, 36(10): 1–8, 2005; Published online in Wiley InterScience (www.interscience. wiley.com). DOI 10.1002/scj.20361</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="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 001228 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001228 | 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:8B8AF82F6B7BBDBE581083A574D358ACBA40023A
|texte= Video text recognition using category‐dependent feature extraction based on feature compensation
}}
| This area was generated with Dilib version V0.6.32. |  |