DocumentCode :
3120000
Title :
Research on Chinese character recognition post-processing based on genetic algorithm
Author :
Wang, Ke-jian ; Tian, Xue-dong ; Guo, Bao-lan
Author_Institution :
Sch. of Math. & Comput., Hebei Univ., Baoding, China
Volume :
4
fYear :
2002
fDate :
4-5 Nov. 2002
Firstpage :
1718
Abstract :
In order to improve the accuracy of a character recognition system, especially to improve recognition rate, it is positively significant to introduce an excellent post-processing method. A Chinese character recognition post-processing (CCRP) based on genetic algorithm is introduced in this paper. The genetic algorithm relies on the Chinese character itself and context information. Experiment shows that this method obtains quite good result. The character recognition rate of the tested text is from 94.99% to 95.92% after post-processing and improves 0.93%.
Keywords :
character recognition; genetic algorithms; CCRP; Chinese character recognition post-processing; GA; genetic algorithm; Character recognition; Error analysis; Error correction; Genetic algorithms; Genetic mutations; Mathematics; Natural languages; Statistics; Testing; Text recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Learning and Cybernetics, 2002. Proceedings. 2002 International Conference on
Print_ISBN :
0-7803-7508-4
Type :
conf
DOI :
10.1109/ICMLC.2002.1175329
Filename :
1175329
Link To Document :
بازگشت