File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: KNOWLEDGE-BASED STROKE-MATCHING METHOD FOR CHINESE CHARACTER RECOGNITION.

TitleKNOWLEDGE-BASED STROKE-MATCHING METHOD FOR CHINESE CHARACTER RECOGNITION.
Authors
Issue Date1988
Citation
Journal of the American Academy of Psychoanalysis, 1988, v. 16 n. 1, p. 993-1003 How to Cite?
AbstractThe character set used by the Chinese is greater in both size and complexity than that used by the Japanese, and experiments performed by the authors indicate that the Yamamoto-Rosenfeld stroke-matching algorithm is too computationally intensive to be implemented for the recognition of complicated Chinese characters. A modified relaxation method that greatly reduces the computational load is proposed. The idea is to incorporate specific knowledge about the Chinese characters into the training system to remove inconsistencies with a higher efficiency and to speed up the matching process. Experimental results on the 240 most frequently used characters written by 37 different individuals showed that a fourfold improvement in speed could be achieved, making it more feasible to implement the algorithm for the recognition of complicated Chinese characters.
Persistent Identifierhttp://hdl.handle.net/10722/154872
ISSN
1997 Impact Factor: 1.345

 

DC FieldValueLanguage
dc.contributor.authorLeung, CheungHoien_US
dc.contributor.authorCheung, YSen_US
dc.contributor.authorWong, YLen_US
dc.date.accessioned2012-08-08T08:30:59Z-
dc.date.available2012-08-08T08:30:59Z-
dc.date.issued1988en_US
dc.identifier.citationJournal of the American Academy of Psychoanalysis, 1988, v. 16 n. 1, p. 993-1003en_US
dc.identifier.issn0018-9472en_US
dc.identifier.urihttp://hdl.handle.net/10722/154872-
dc.description.abstractThe character set used by the Chinese is greater in both size and complexity than that used by the Japanese, and experiments performed by the authors indicate that the Yamamoto-Rosenfeld stroke-matching algorithm is too computationally intensive to be implemented for the recognition of complicated Chinese characters. A modified relaxation method that greatly reduces the computational load is proposed. The idea is to incorporate specific knowledge about the Chinese characters into the training system to remove inconsistencies with a higher efficiency and to speed up the matching process. Experimental results on the 240 most frequently used characters written by 37 different individuals showed that a fourfold improvement in speed could be achieved, making it more feasible to implement the algorithm for the recognition of complicated Chinese characters.en_US
dc.languageengen_US
dc.relation.ispartofIEEE Transactions on Systems, Man and Cyberneticsen_US
dc.titleKNOWLEDGE-BASED STROKE-MATCHING METHOD FOR CHINESE CHARACTER RECOGNITION.en_US
dc.typeArticleen_US
dc.identifier.emailLeung, CheungHoi:chleung@eee.hku.hken_US
dc.identifier.emailCheung, YS:paul.cheung@hku.hken_US
dc.identifier.authorityLeung, CheungHoi=rp00146en_US
dc.identifier.authorityCheung, YS=rp00077en_US
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.scopuseid_2-s2.0-17144468611en_US
dc.identifier.volumeSMC-17en_US
dc.identifier.issue6en_US
dc.identifier.spage993en_US
dc.identifier.epage1003en_US
dc.identifier.scopusauthoridLeung, CheungHoi=7402612415en_US
dc.identifier.scopusauthoridCheung, YS=7202595335en_US
dc.identifier.scopusauthoridWong, YL=36853077200en_US

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats