File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Recognition of handwritten Chinese characters by critical region analysis

TitleRecognition of handwritten Chinese characters by critical region analysis
Authors
KeywordsConfusing pair
Distorted sample
ETL-9B database
Fisher's linear discriminant
Handwritten Chinese character recognition
Regularization
Issue Date2010
PublisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/pr
Citation
Pattern Recognition, 2010, v. 43 n. 3, p. 949-961 How to Cite?
AbstractThe problem of recognizing offline handwritten Chinese characters has been investigated extensively. One difficulty is due to the existence of characters with very similar shapes. In this paper, we propose a "critical region analysis" technique which highlights the critical regions that distinguish one character from another similar character. The critical regions are identified automatically based on the output of the Fisher's discriminant. Additional features are extracted from these regions and contribute to the recognition process. By incorporating this technique into the character recognition system, a record high recognition rate of 99.53% on the ETL-9B database is obtained. © 2009 Elsevier Ltd. All rights reserved.
Persistent Identifierhttp://hdl.handle.net/10722/124708
ISSN
2015 Impact Factor: 3.399
2015 SCImago Journal Rankings: 2.051
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorLeung, KCen_HK
dc.contributor.authorLeung, CHen_HK
dc.date.accessioned2010-10-31T10:49:40Z-
dc.date.available2010-10-31T10:49:40Z-
dc.date.issued2010en_HK
dc.identifier.citationPattern Recognition, 2010, v. 43 n. 3, p. 949-961en_HK
dc.identifier.issn0031-3203en_HK
dc.identifier.urihttp://hdl.handle.net/10722/124708-
dc.description.abstractThe problem of recognizing offline handwritten Chinese characters has been investigated extensively. One difficulty is due to the existence of characters with very similar shapes. In this paper, we propose a "critical region analysis" technique which highlights the critical regions that distinguish one character from another similar character. The critical regions are identified automatically based on the output of the Fisher's discriminant. Additional features are extracted from these regions and contribute to the recognition process. By incorporating this technique into the character recognition system, a record high recognition rate of 99.53% on the ETL-9B database is obtained. © 2009 Elsevier Ltd. All rights reserved.en_HK
dc.languageengen_HK
dc.publisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/pren_HK
dc.relation.ispartofPattern Recognitionen_HK
dc.subjectConfusing pairen_HK
dc.subjectDistorted sampleen_HK
dc.subjectETL-9B databaseen_HK
dc.subjectFisher's linear discriminanten_HK
dc.subjectHandwritten Chinese character recognitionen_HK
dc.subjectRegularizationen_HK
dc.titleRecognition of handwritten Chinese characters by critical region analysisen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0031-3203&volume=43&spage=949&epage=961&date=2010&atitle=Recognition+of+handwritten+Chinese+characters+by+critical+region+analysisen_HK
dc.identifier.emailLeung, KC:kcleung@eee.hku.hken_HK
dc.identifier.emailLeung, CH:chleung@eee.hku.hken_HK
dc.identifier.authorityLeung, KC=rp00147en_HK
dc.identifier.authorityLeung, CH=rp00146en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.patcog.2009.09.001en_HK
dc.identifier.scopuseid_2-s2.0-70449710788en_HK
dc.identifier.hkuros181377en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-70449710788&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume43en_HK
dc.identifier.issue3en_HK
dc.identifier.spage949en_HK
dc.identifier.epage961en_HK
dc.identifier.isiWOS:000273094100037-
dc.publisher.placeNetherlandsen_HK
dc.identifier.scopusauthoridLeung, KC=7401860663en_HK
dc.identifier.scopusauthoridLeung, CH=7402612415en_HK
dc.identifier.citeulike5826261-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats