Title :
Printed Chinese character recognition via the cooperative block neural networks
Author :
Xu, Ning ; Ding, Xiaoqing
Author_Institution :
Dept. of Electron. Eng., Tsinghua Univ., Beijing, China
Abstract :
In this paper, the authors propose a new architecture of artificial neural networks, which is called the cooperative block neural networks (CBNN), and use it for the recognition of multi-font printed Chinese characters. Preliminary simulation results have proven that in tackling the difficulties associated with sophisticated topological structures of characters and the large number of Chinese characters to be recognized, the CBNN system is successful
Keywords :
neural nets; optical character recognition; architecture; artificial neural networks; cooperative block neural networks; multi-font printed Chinese characters; optical character recognition; simulation; Artificial intelligence; Artificial neural networks; Character recognition; Classification tree analysis; Data mining; Decision theory; Decision trees; Feature extraction; Neural networks; Statistical analysis;
Conference_Titel :
Industrial Electronics, 1992., Proceedings of the IEEE International Symposium on
Conference_Location :
Xian
Print_ISBN :
0-7803-0042-4
DOI :
10.1109/ISIE.1992.279580
