File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: A discrete contextual stochastic model for the off-line recognition of handwritten Chinese characters

TitleA discrete contextual stochastic model for the off-line recognition of handwritten Chinese characters
Authors
KeywordsContextual stochastic model
Discriminative training
Markov random field
Offline recognition of handwritten Chinese characters
Issue Date2001
PublisherIEEE. The Journal's web site is located at http://www.computer.org/tpami
Citation
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, v. 23 n. 7, p. 774-782 How to Cite?
AbstractWe study a discrete contextual stochastic (CS) model for complex and variant patterns like handwritten Chinese characters. Three fundamental problems of using CS models for character recognition are discussed, and several practical techniques for solving these problems are investigated. A formulation for discriminative training of CS model parameters is also introduced and its practical usage investigated. To illustrate the characteristics of the various algorithms, comparative experiments are performed on a recognition task with a vocabulary consisting of 50 pairs of highly similar handwritten Chinese characters. The experimental results confirm the effectiveness of the discriminative training for improving recognition performance.
Persistent Identifierhttp://hdl.handle.net/10722/43658
ISSN
2023 Impact Factor: 20.8
2023 SCImago Journal Rankings: 6.158
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorXiong, Yen_HK
dc.contributor.authorHuo, Qen_HK
dc.contributor.authorChan, Cen_HK
dc.date.accessioned2007-03-23T04:51:25Z-
dc.date.available2007-03-23T04:51:25Z-
dc.date.issued2001en_HK
dc.identifier.citationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, v. 23 n. 7, p. 774-782en_HK
dc.identifier.issn0162-8828en_HK
dc.identifier.urihttp://hdl.handle.net/10722/43658-
dc.description.abstractWe study a discrete contextual stochastic (CS) model for complex and variant patterns like handwritten Chinese characters. Three fundamental problems of using CS models for character recognition are discussed, and several practical techniques for solving these problems are investigated. A formulation for discriminative training of CS model parameters is also introduced and its practical usage investigated. To illustrate the characteristics of the various algorithms, comparative experiments are performed on a recognition task with a vocabulary consisting of 50 pairs of highly similar handwritten Chinese characters. The experimental results confirm the effectiveness of the discriminative training for improving recognition performance.en_HK
dc.format.extent218106 bytes-
dc.format.extent27136 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypeapplication/msword-
dc.languageengen_HK
dc.publisherIEEE. The Journal's web site is located at http://www.computer.org/tpamien_HK
dc.relation.ispartofIEEE Transactions on Pattern Analysis and Machine Intelligence-
dc.rights©2001 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.-
dc.subjectContextual stochastic model-
dc.subjectDiscriminative training-
dc.subjectMarkov random field-
dc.subjectOffline recognition of handwritten Chinese characters-
dc.titleA discrete contextual stochastic model for the off-line recognition of handwritten Chinese charactersen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0162-8828&volume=23&issue=7&spage=774&epage=782&date=2001&atitle=A+discrete+contextual+stochastic+model+for+the+off-line+recognition+of+handwritten+Chinese+charactersen_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/34.935851en_HK
dc.identifier.scopuseid_2-s2.0-0035392890-
dc.identifier.hkuros69416-
dc.identifier.isiWOS:000169704000008-
dc.identifier.issnl0162-8828-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats