File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Off-line Chinese handwriting recognition using multi-stage neural network architecture

TitleOff-line Chinese handwriting recognition using multi-stage neural network architecture
Authors
KeywordsComputers
Artificial intelligence
Issue Date1995
PublisherIEEE.
Citation
Ieee International Conference On Neural Networks - Conference Proceedings, 1995, v. 6, p. 3083-3088 How to Cite?
AbstractIn this paper, we propose a Multi-stage Neural Network Architecture (MNNA) which integrates several neural networks and various feature extraction approaches into a unique pattern recognition system. General mechanism for designing the MNNA is presented. A three-stage fully connected feedforward neural networks system is designed for Handwritten Chinese Character Recognition (HCCR). Different feature extraction methods are employed at each stage. Experiments show that the three-stage neural network HCCR system has achieved impressive performance and the preliminary results are very encouraging.
Persistent Identifierhttp://hdl.handle.net/10722/45565
ISSN

 

DC FieldValueLanguage
dc.contributor.authorJin, Lianwenen_HK
dc.contributor.authorChan, Kwokpingen_HK
dc.contributor.authorXu, Bingzhengen_HK
dc.date.accessioned2007-10-30T06:29:18Z-
dc.date.available2007-10-30T06:29:18Z-
dc.date.issued1995en_HK
dc.identifier.citationIeee International Conference On Neural Networks - Conference Proceedings, 1995, v. 6, p. 3083-3088en_HK
dc.identifier.issn1098-7576en_HK
dc.identifier.urihttp://hdl.handle.net/10722/45565-
dc.description.abstractIn this paper, we propose a Multi-stage Neural Network Architecture (MNNA) which integrates several neural networks and various feature extraction approaches into a unique pattern recognition system. General mechanism for designing the MNNA is presented. A three-stage fully connected feedforward neural networks system is designed for Handwritten Chinese Character Recognition (HCCR). Different feature extraction methods are employed at each stage. Experiments show that the three-stage neural network HCCR system has achieved impressive performance and the preliminary results are very encouraging.en_HK
dc.format.extent556496 bytes-
dc.format.extent4345 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypetext/plain-
dc.languageengen_HK
dc.publisherIEEE.en_HK
dc.relation.ispartofIEEE International Conference on Neural Networks - Conference Proceedingsen_HK
dc.rights©1995 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.en_HK
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.subjectComputersen_HK
dc.subjectArtificial intelligenceen_HK
dc.titleOff-line Chinese handwriting recognition using multi-stage neural network architectureen_HK
dc.typeConference_Paperen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=1098-7576&volume=6&spage=3083&epage=3088&date=1995&atitle=Off-line+Chinese+handwriting+recognition+using+multi-stage+neural+network+architectureen_HK
dc.identifier.emailChan, Kwokping:kpchan@cs.hku.hken_HK
dc.identifier.authorityChan, Kwokping=rp00092en_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/ICNN.1995.487276en_HK
dc.identifier.scopuseid_2-s2.0-0029545697en_HK
dc.identifier.hkuros14159-
dc.identifier.volume6en_HK
dc.identifier.spage3083en_HK
dc.identifier.epage3088en_HK
dc.identifier.scopusauthoridJin, Lianwen=7403329268en_HK
dc.identifier.scopusauthoridChan, Kwokping=7406032820en_HK
dc.identifier.scopusauthoridXu, Bingzheng=7404588354en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats