Title :
A new stroke-based directional feature extraction approach for handwritten Chinese character recognition
Author :
Gao, Xue ; Jin, Lian-wen ; Yin, Jun-Xun ; Huang, Jian-Cheng
Author_Institution :
Dept. of Electron. & Commun. Eng., South China Univ. of Technol., Guangzhou, China
fDate :
6/23/1905 12:00:00 AM
Abstract :
A directional feature extraction approach based on stroke directional decomposition of a Chinese character is proposed. Without extracting the skeleton or contour of the character, the four directional sub-patterns, namely, horizontal (-), vertical (|), left up diagonal (/) and right up diagonal () sub-patterns could be obtained directly from analyzing the stroke directional characteristics of the character. Five kinds of line-density based elastic meshing methods are presented to extract cellular directional features. Experimentation on a total of 18800 handwritten samples from 940 categories produces a recognition rate of 92.71%, showing the effectiveness of the proposed approach
Keywords :
feature extraction; handwritten character recognition; natural languages; Chinese character decomposition; cellular directional features; directional sub-patterns; handwritten Chinese character recognition; handwritten samples; line-density based elastic meshing methods; recognition rate; stroke directional characteristics; stroke directional decomposition; stroke-based directional feature extraction approach; Character recognition; Data mining; Equations; Feature extraction; Handwriting recognition; Image segmentation; Natural languages; Pixel; Skeleton; Writing;
Conference_Titel :
Document Analysis and Recognition, 2001. Proceedings. Sixth International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7695-1263-1
DOI :
10.1109/ICDAR.2001.953867