Title :
Multi-channel handwritten digit recognition using neural networks
Author :
Chi, Zheru ; Lu, Zhongkang ; Chan, Fai-hung
Author_Institution :
Dept. of Electron. Eng., Hong Kong Polytech. Univ., Kowloon, Hong Kong
Abstract :
Human recognition is much more robust than machine recognition in dealing with rotated and noisy patterns. In this paper, we present a multi-channel neural network (MCNN) approach for handwritten digit recognition based on the human recognition experience in the hope of achieving human-like performance. In this approach, three neural net work modules are trained individually by using three different set of features, intensity-based, rotation invariant, and noise deducted features. The outputs of these three modules are then combined by a combination neural network which is trained separately. Experimental results on a database of 1900 digit patterns written by 190 people show that a recognition rate of 89.5% is obtained on an independent test set that includes both the rotated and noisy data
Keywords :
backpropagation; feature extraction; handwriting recognition; neural nets; combination neural network; intensity-based features; multi-channel handwritten digit recognition; multichannel neural network; noise deducted features; rotation invariant features; Character recognition; Feature extraction; Frequency domain analysis; Handwriting recognition; Humans; Neural networks; Pattern recognition; Robustness; Spatial databases; Testing;
Conference_Titel :
Circuits and Systems, 1997. ISCAS '97., Proceedings of 1997 IEEE International Symposium on
Print_ISBN :
0-7803-3583-X
DOI :
10.1109/ISCAS.1997.608900