Title :
A neural network structure for feature extraction and recognition of handwritten digits
Author :
Zhang, Liming ; Qu, Donghui
Author_Institution :
Dept. of Electron. Eng., Fudan Univ., Shanghai, China
Abstract :
The authors suggest some criteria of feature extraction for distinguishing numeric handwritten character. According to the criteria, 27-dimension feature vectors are chosen from a training set. Thus some of them can be obtained by neural networks. A back-propagation network is used to classify a test set. The recognition rate performance on 2000 characters written by 200 people is 94%
Keywords :
character recognition; computerised pattern recognition; neural nets; back-propagation network; feature extraction; handwritten digits; neural network structure; training set; Artificial neural networks; Cellular neural networks; Character recognition; Constraint theory; Feature extraction; Handwriting recognition; Nearest neighbor searches; Neural networks; Testing; Writing;
Conference_Titel :
Circuits and Systems, 1991. Conference Proceedings, China., 1991 International Conference on
Conference_Location :
Shenzhen
DOI :
10.1109/CICCAS.1991.184343
