File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Character segmentation algorithm for off-line handwritten script recognition

TitleCharacter segmentation algorithm for off-line handwritten script recognition
Authors
Issue Date1995
PublisherS P I E - International Society for Optical Engineering. The Journal's web site is located at http://spie.org/x1848.xml
Citation
Proceedings Of Spie - The International Society For Optical Engineering, 1995, v. 2501 n. 3/-, p. 1656-1667 How to Cite?
AbstractIn this paper, a new character segmentation algorithm for dealing with off-line handwritten script recognition is presented. The X-axis projection, Y-axis projection and geometric classes techniques used by the algorithm proves to be successful in segmenting normal handwriting with a success rate of 93.5%. As a result of this development, detailed understanding of geometric classes of English characters and the difficult cases in segmentation was gained. Although the algorithm works quite well with a randomly chosen sample, results of a detailed analysis may shed new light into the tuning of the algorithm especially for segmenting the identified difficult cases.
Persistent Identifierhttp://hdl.handle.net/10722/158156
ISSN

 

DC FieldValueLanguage
dc.contributor.authorYung, Nelson Hen_US
dc.contributor.authorLai, Andrew Hen_US
dc.contributor.authorChua, Perry Zen_US
dc.date.accessioned2012-08-08T08:58:18Z-
dc.date.available2012-08-08T08:58:18Z-
dc.date.issued1995en_US
dc.identifier.citationProceedings Of Spie - The International Society For Optical Engineering, 1995, v. 2501 n. 3/-, p. 1656-1667en_US
dc.identifier.issn0277-786Xen_US
dc.identifier.urihttp://hdl.handle.net/10722/158156-
dc.description.abstractIn this paper, a new character segmentation algorithm for dealing with off-line handwritten script recognition is presented. The X-axis projection, Y-axis projection and geometric classes techniques used by the algorithm proves to be successful in segmenting normal handwriting with a success rate of 93.5%. As a result of this development, detailed understanding of geometric classes of English characters and the difficult cases in segmentation was gained. Although the algorithm works quite well with a randomly chosen sample, results of a detailed analysis may shed new light into the tuning of the algorithm especially for segmenting the identified difficult cases.en_US
dc.languageengen_US
dc.publisherS P I E - International Society for Optical Engineering. The Journal's web site is located at http://spie.org/x1848.xmlen_US
dc.relation.ispartofProceedings of SPIE - The International Society for Optical Engineeringen_US
dc.titleCharacter segmentation algorithm for off-line handwritten script recognitionen_US
dc.typeConference_Paperen_US
dc.identifier.emailYung, Nelson H:nyung@eee.hku.hken_US
dc.identifier.authorityYung, Nelson H=rp00226en_US
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.scopuseid_2-s2.0-0029214991en_US
dc.identifier.volume2501en_US
dc.identifier.issue3/-en_US
dc.identifier.spage1656en_US
dc.identifier.epage1667en_US
dc.publisher.placeUnited Statesen_US
dc.identifier.scopusauthoridYung, Nelson H=7003473369en_US
dc.identifier.scopusauthoridLai, Andrew H=7102225794en_US
dc.identifier.scopusauthoridChua, Perry Z=7004944821en_US

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats