File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: A Study On the Use of 8-Directional Features For Online Handwritten Chinese Character Recognition

TitleA Study On the Use of 8-Directional Features For Online Handwritten Chinese Character Recognition
Authors
Bai, ZHuo, Q
KeywordsGabor filters
Gaussian processes
Feature extraction
Handwritten character recognition
Issue Date2005
PublisherIEEE Computer Society.
Citation
8th International Conference on Document Analysis and Recognition (ICDAR 2005), Seoul, South Korea, August 29 - September 1, 2005. In Eighth International Conference on Document Analysis and Recognition (ICDAR'05), 2005, v. 1, p. 262-266 How to Cite?
DOI: http://dx.doi.org/10.1109/ICDAR.2005.34
AbstractThis paper presents a study of using 8-directional features for online handwritten Chinese character recognition. Given an online handwritten character sample, a series of processing steps, including linear size normalization, adding imaginary strokes, nonlinear shape normalization, equidistance resampling, and smoothing, are performed to derive a 64 × 64 normalized online character sample. Then, 8-directional features are extracted from each online trajectory point, and 8 directional pattern images are generated accordingly, from which blurred directional features are extracted at 8 × 8 uniformly sampled locations using a filter derived from the Gaussian envelope of a Gabor filter. Finally, a 512-dimensional vector of raw features is formed. Extensive experiments on the task of recognizing 3755 level-1 Chinese characters in GB2312-80 standard are performed to compare and discern the best setting for several algorithmic choices and control parameters. The effectiveness of the studied approach is confirmed.
Persistent Identifierhttp://hdl.handle.net/10722/53608
ISBN
0-7695-2420-6
ISSN
1520-5363
2020 SCImago Journal Rankings: 0.353

 

DC FieldValueLanguage
dc.contributor.authorBai, Zen_HK
dc.contributor.authorHuo, Qen_HK
dc.date.accessioned2009-04-03T07:24:32Z-
dc.date.available2009-04-03T07:24:32Z-
dc.date.issued2005en_HK
dc.identifier.citation8th International Conference on Document Analysis and Recognition (ICDAR 2005), Seoul, South Korea, August 29 - September 1, 2005. In Eighth International Conference on Document Analysis and Recognition (ICDAR'05), 2005, v. 1, p. 262-266en_HK
dc.identifier.isbn0-7695-2420-6-
dc.identifier.issn1520-5363-
dc.identifier.urihttp://hdl.handle.net/10722/53608-
dc.description.abstractThis paper presents a study of using 8-directional features for online handwritten Chinese character recognition. Given an online handwritten character sample, a series of processing steps, including linear size normalization, adding imaginary strokes, nonlinear shape normalization, equidistance resampling, and smoothing, are performed to derive a 64 × 64 normalized online character sample. Then, 8-directional features are extracted from each online trajectory point, and 8 directional pattern images are generated accordingly, from which blurred directional features are extracted at 8 × 8 uniformly sampled locations using a filter derived from the Gaussian envelope of a Gabor filter. Finally, a 512-dimensional vector of raw features is formed. Extensive experiments on the task of recognizing 3755 level-1 Chinese characters in GB2312-80 standard are performed to compare and discern the best setting for several algorithmic choices and control parameters. The effectiveness of the studied approach is confirmed.-
dc.languageengen_HK
dc.publisherIEEE Computer Society.en_HK
dc.relation.ispartofEighth International Conference on Document Analysis and Recognition (ICDAR'05)-
dc.rights©2005 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.subjectGabor filtersen_HK
dc.subjectGaussian processesen_HK
dc.subjectFeature extractionen_HK
dc.subjectHandwritten character recognitionen_HK
dc.titleA Study On the Use of 8-Directional Features For Online Handwritten Chinese Character Recognitionen_HK
dc.typeConference_Paperen_HK
dc.identifier.emailHuo, Q: qhuo@cs.hku.hken_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/ICDAR.2005.34-
dc.identifier.scopuseid_2-s2.0-33947424805-
dc.identifier.hkuros101983-
dc.identifier.issnl1520-5363-

Export via OAI-PMH Interface in XML Formats

OR

Export to Other Non-XML Formats