One-dimensional representation of two-dimensional information for HMM based handwriting recognition
Identifieur interne : 001C55 ( Main/Exploration ); précédent : 001C54; suivant : 001C56One-dimensional representation of two-dimensional information for HMM based handwriting recognition
Auteurs : N. Arica [Turquie] ; F. T. Yarman-Vural [Turquie]Source :
- Pattern Recognition Letters [ 0167-8655 ] ; 1999.
Abstract
In this study, we introduce a one-dimensional feature set, which embeds two-dimensional information into an observation sequence of one-dimensional string, selected from a code-book. It provides a consistent normalization among distinct classes of shapes, which is very convenient for Hidden Markov Model (HMM) based shape recognition schemes. The normalization parameters, which maximize the recognition rate, are dynamically estimated in the training stage of HMM. The proposed recognition system is tested on handwritten data of the National Institute of Standards and Technology (NIST) database and a local database. The experimental results indicate very high recognition rates.
Url:
DOI: 10.1016/S0167-8655(00)00023-4
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000983
- to stream Istex, to step Curation: 000972
- to stream Istex, to step Checkpoint: 001257
- to stream Main, to step Merge: 001D54
- to stream Main, to step Curation: 001C55
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>One-dimensional representation of two-dimensional information for HMM based handwriting recognition</title><author><name sortKey="Arica, N" sort="Arica, N" uniqKey="Arica N" first="N." last="Arica">N. Arica</name></author><author><name sortKey="Yarman Vural, F T" sort="Yarman Vural, F T" uniqKey="Yarman Vural F" first="F. T." last="Yarman-Vural">F. T. Yarman-Vural</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:7CEAAF8AA4822F2513D653B4AF4E3D028A991350</idno><date when="2000" year="2000">2000</date><idno type="doi">10.1016/S0167-8655(00)00023-4</idno><idno type="url">https://api.istex.fr/document/7CEAAF8AA4822F2513D653B4AF4E3D028A991350/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000983</idno><idno type="wicri:Area/Istex/Curation">000972</idno><idno type="wicri:Area/Istex/Checkpoint">001257</idno><idno type="wicri:doubleKey">0167-8655:2000:Arica N:one:dimensional:representation</idno><idno type="wicri:Area/Main/Merge">001D54</idno><idno type="wicri:Area/Main/Curation">001C55</idno><idno type="wicri:Area/Main/Exploration">001C55</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a">One-dimensional representation of two-dimensional information for HMM based handwriting recognition</title><author><name sortKey="Arica, N" sort="Arica, N" uniqKey="Arica N" first="N." last="Arica">N. Arica</name><affiliation wicri:level="1"><country xml:lang="fr">Turquie</country><wicri:regionArea>Department of Computer Engineering, Middle East Technical University, 06531, Ankara</wicri:regionArea><wicri:noRegion>Ankara</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Turquie</country></affiliation></author><author><name sortKey="Yarman Vural, F T" sort="Yarman Vural, F T" uniqKey="Yarman Vural F" first="F. T." last="Yarman-Vural">F. T. Yarman-Vural</name><affiliation wicri:level="1"><country xml:lang="fr">Turquie</country><wicri:regionArea>Department of Computer Engineering, Middle East Technical University, 06531, Ankara</wicri:regionArea><wicri:noRegion>Ankara</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Turquie</country></affiliation></author></analytic><monogr></monogr><series><title level="j">Pattern Recognition Letters</title><title level="j" type="abbrev">PATREC</title><idno type="ISSN">0167-8655</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="1999">1999</date><biblScope unit="volume">21</biblScope><biblScope unit="issue">6–7</biblScope><biblScope unit="page" from="583">583</biblScope><biblScope unit="page" to="592">592</biblScope></imprint><idno type="ISSN">0167-8655</idno></series><idno type="istex">7CEAAF8AA4822F2513D653B4AF4E3D028A991350</idno><idno type="DOI">10.1016/S0167-8655(00)00023-4</idno><idno type="PII">S0167-8655(00)00023-4</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0167-8655</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">In this study, we introduce a one-dimensional feature set, which embeds two-dimensional information into an observation sequence of one-dimensional string, selected from a code-book. It provides a consistent normalization among distinct classes of shapes, which is very convenient for Hidden Markov Model (HMM) based shape recognition schemes. The normalization parameters, which maximize the recognition rate, are dynamically estimated in the training stage of HMM. The proposed recognition system is tested on handwritten data of the National Institute of Standards and Technology (NIST) database and a local database. The experimental results indicate very high recognition rates.</div></front></TEI><affiliations><list><country><li>Turquie</li></country></list><tree><country name="Turquie"><noRegion><name sortKey="Arica, N" sort="Arica, N" uniqKey="Arica N" first="N." last="Arica">N. Arica</name></noRegion><name sortKey="Arica, N" sort="Arica, N" uniqKey="Arica N" first="N." last="Arica">N. Arica</name><name sortKey="Yarman Vural, F T" sort="Yarman Vural, F T" uniqKey="Yarman Vural F" first="F. T." last="Yarman-Vural">F. T. Yarman-Vural</name><name sortKey="Yarman Vural, F T" sort="Yarman Vural, F T" uniqKey="Yarman Vural F" first="F. T." last="Yarman-Vural">F. T. Yarman-Vural</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 001C55 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001C55 | 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:7CEAAF8AA4822F2513D653B4AF4E3D028A991350
|texte= One-dimensional representation of two-dimensional information for HMM based handwriting recognition
}}
| This area was generated with Dilib version V0.6.32. |  |