DocumentCode
2484064
Title
Segmentation-free recognizer based on enhanced four plane feature for realistic Chinese handwriting
Author
Su, Tong-Hua ; Zhang, Tian-Wen ; Huang, Hu-Jie ; Liu, Cheng-Lin
Author_Institution
Sch. of Comput. Sci. & Technol., Harbin Inst. of Technol., Harbin
fYear
2008
fDate
8-11 Dec. 2008
Firstpage
1
Lastpage
4
Abstract
Directional features are preferred in off-line Chinese character recognition due to their superior performance. This paper proposes an enhanced four plane feature (en-FPF) within a segmentation-free recognition framework. First, the directional planes are strengthened by replenishing salient pixels. Second, the method to count perpendicular strokes are renewed. In experiments of realistic Chinese handwriting recognition, the proposed enhancement yields desirable improvements of recognition rates, especially to punctuation marks and digits. Compared with four-orientation Gradient feature and Gabor feature, the superiority of en-FPF is also observed.
Keywords
handwriting recognition; handwritten character recognition; Chinese character recognition; Gabor feature; directional feature; directional planes; enhanced four plane feature; gradient feature; perpendicular strokes; realistic Chinese handwriting recognition; salient pixels; segmentation-free recognition framework; segmentation-free recognizer; Automation; Character recognition; Computer science; Feature extraction; Handwriting recognition; Image segmentation; Laboratories; Natural languages; Pattern recognition; Writing;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition, 2008. ICPR 2008. 19th International Conference on
Conference_Location
Tampa, FL
ISSN
1051-4651
Print_ISBN
978-1-4244-2174-9
Electronic_ISBN
1051-4651
Type
conf
DOI
10.1109/ICPR.2008.4761543
Filename
4761543
Link To Document