DocumentCode
1138791
Title
Handwritten Chinese radical recognition using nonlinear active shape models
Author
Shi, D. ; Gunn, S.R. ; Damper, R.I.
Author_Institution
Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, Singapore
Volume
25
Issue
2
fYear
2003
fDate
2/1/2003 12:00:00 AM
Firstpage
277
Lastpage
280
Abstract
Handwritten Chinese characters can be recognized by first extracting the basic shapes (radicals) of which they are composed. Radicals are described by nonlinear active shape models and optimal parameters found using the chamfer distance transform and a dynamic tunneling algorithm. The radical recognition rate is 96.5 percent correct (writer-independent) on 280,000 characters containing 98 radical classes.
Keywords
handwritten character recognition; optical character recognition; optimisation; chamfer distance transform; dynamic tunneling algorithm; handwritten Chinese radical recognition; nonlinear active shape models; optimal parameters; radical extraction; radical recognition rate; Active shape model; Character recognition; Data mining; Deformable models; Gunn devices; Handwriting recognition; Heuristic algorithms; Polynomials; Principal component analysis; Tunneling;
fLanguage
English
Journal_Title
Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publisher
ieee
ISSN
0162-8828
Type
jour
DOI
10.1109/TPAMI.2003.1177158
Filename
1177158
Link To Document