Title :
A neural network based classifier for handwritten Chinese character recognition
Author :
Wu, Mingrui ; Zhang, Bo ; Zhang, Ling
Author_Institution :
State Key Lab. of Intelligent Technol. & Syst., Beijing, China
Abstract :
In this paper, a geometrical approach for building neural networks is proposed. With the proposed approach, it is very easy to construct an efficient neural classifier to solve the handwritten Chinese character recognition problem, as well as other pattern recognition problems of large scale. Experiments are conducted to evaluate the performance of the proposed approach and results obtained are promising
Keywords :
computational geometry; handwritten character recognition; neural nets; pattern classification; character recognition; geometrical representation; handwritten Chinese character; neural classifier; neural networks; sphere neighbourhood coverage; Character recognition; Computer science; Handwriting recognition; Intelligent systems; Laboratories; Large-scale systems; Neural networks; Neurons; Pattern recognition; Solid modeling;
Conference_Titel :
Pattern Recognition, 2000. Proceedings. 15th International Conference on
Conference_Location :
Barcelona
Print_ISBN :
0-7695-0750-6
DOI :
10.1109/ICPR.2000.906136
