DocumentCode
2454689
Title
Off-line handwritten Chinese character stroke extraction
Author
Lin, Feng ; Tang, Xiaoou
Author_Institution
Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Shatin, China
Volume
3
fYear
2002
fDate
2002
Firstpage
249
Abstract
Stroke extraction is of great significance for an offline character recognition system. In this paper, we present an efficient stroke extraction method based on a combination of a simple feature point detection scheme and a novel stroke segment connecting method. The algorithm can rapidly and accurately extract the strokes from the thinned Chinese character images. Experimental results show that over 99% accuracy was achieved on a large data set with over eighteen thousand character strokes.
Keywords
feature extraction; graph theory; handwritten character recognition; image segmentation; bidirectional graph; character skeleton; feature point detection; fork points; handwritten Chinese character recognition; off line system; stroke extraction; stroke segment connecting method; thinned images; Character recognition; Computational efficiency; Data mining; Feature extraction; Gray-scale; Handwriting recognition; Image analysis; Joining processes; Pixel; Skeleton;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition, 2002. Proceedings. 16th International Conference on
ISSN
1051-4651
Print_ISBN
0-7695-1695-X
Type
conf
DOI
10.1109/ICPR.2002.1047841
Filename
1047841
Link To Document