DocumentCode :
2423597
Title :
A feature-preserved thinning algorithm for handwritten Chinese characters
Author :
Chiu, Hung-Pin ; Tseng, Din-Chang
Author_Institution :
Inst. of Comput. Sci. & Inf. Eng., Nat. Central Univ., Chung-Li, Taiwan
Volume :
3
fYear :
1996
fDate :
25-29 Aug 1996
Firstpage :
235
Abstract :
This paper proposes a feature-preserved thinning algorithm for handwritten Chinese characters. One stroke that crosses or connects other strokes is divided into segments based on the direction runs in the stroke. Four directions are represented by four direction codes and one of four direction codes is assigned to each black pixel. Connected pixels with the same direction code form a block. We split blocks into stroke and fork segments according to the direction codes of blocks and the adjacent relationships among the blocks. The skeletons of the stroke segments are extracted; no skeleton point is extracted in the fork segments. Skeleton segments that connect to one fork segment are joined to reconstruct complete stroke skeletons by replacing the fork segment with line segments. The four directions are just used to split strokes; the thinned strokes are still in any possible direction. The proposed approach is free from the Y-shape distortion, L-shape distortion, hairy problem, shortening problem, and hole problem
Keywords :
character recognition; image reconstruction; image segmentation; L-shape distortion; Y-shape distortion; feature-preserved thinning algorithm; fork segments; hairy problem; handwritten Chinese characters; hole problem; line segments; segmentation; shortening problem; stroke direction runs; stroke skeletons; Character recognition; Computer science; Data preprocessing; Handwriting recognition; Image analysis; Image reconstruction; Optical character recognition software; Optical distortion; Shape; Skeleton;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition, 1996., Proceedings of the 13th International Conference on
Conference_Location :
Vienna
ISSN :
1051-4651
Print_ISBN :
0-8186-7282-X
Type :
conf
DOI :
10.1109/ICPR.1996.546945
Filename :
546945
Link To Document :
بازگشت