Title :
Multifont Chinese character recognition using side-stroke-end feature
Author_Institution :
Dept. of Comput. & Syst. Sci., Nankai Univ., Tianjin, China
Abstract :
The side-stroke-end feature (SSEF) of Chinese characters is proposed in order to deal with multifont Chinese character recognition. It is employed as a preclassified feature, so the whole Chinese character set can be divided into smaller groups. Decision trees and meshed features are used for recognizing unknown patterns in each group. This new classifier has been developed. Experimental results show that the recognition rate is higher than 99% and the speed is 40 characters per second
Keywords :
character recognition; character sets; Chinese character set; decision trees; meshed features; multifont Chinese character recognition; preclassified feature; recognition rate; side-stroke-end feature; unknown patterns; Belts; Character recognition; Decision trees; Error analysis; Image recognition; Pattern matching; Pattern recognition; Pixel; Shape; Testing;
Conference_Titel :
Document Analysis and Recognition, 1993., Proceedings of the Second International Conference on
Conference_Location :
Tsukuba Science City
Print_ISBN :
0-8186-4960-7
DOI :
10.1109/ICDAR.1993.395618
