Abstract—Handwritten digit recognition has become very useful in endeavors of human/computer interaction. Reliable, fast, and flexible recognition methodologies have elevated the utility. This paper presents an experiment and analysis of the Neural Network classifier to recognize handwritten digits based on a standard database. The experimental setup implemented in Matlab determines the ability of a Multi-Layer Neural Network to identify handwritten digit samples 5-9. This network is the representative for recognition of remaining digits 0-4. We consider not only accurate recognition rate, but also training time, recognition time as well as the complexity of the networks. The Multi-Layer Perceptron Network (MLPN) was trained by back propagation algorithm. Network structures vary with the hidden units, learning rates, the number of iterations that seem necessary for the network to converge. Different network structures and their corresponding recognition rates are compared in this paper to find the optimal parameters of the Neural Network for this application. Using the optimal parameters, the network performs with an overall recognition rate 94%.

Index Terms—Handwritten Digits, Multi-Layer-Perceptron Neural Network, Network Architecture.

M.J. Islam is a doctoral student of Electrical and Computer Engineering Department, University of Windsor, Windsor, ON N9B3P4, Canada.
Q.M.J. Wu is the Professor of Electrical and Computer Engineering Department, University of Windsor, Windsor, ON, N9B3P4, Canada
M. Ahmadi is the University Professor of Electrical and Computer Engineering Department, University of Windsor, Windsor, ON, N9B3P4,Canada.
M.A. Sid-Ahmed is the Professor and Head of Electrical and Computer Engineering Department, University of Windsor, Windsor, ON, N9B3P4,Canada

Cite: M. J. Islam, Q. M. J. Wu, M. Ahmadi, and M. A. Sid-Ahmed, "Neural Network Based Handwritten Digits Recognition- An Experiment and Analysis," International Journal of Computer and Electrical Engineering vol. 1, no. 2, pp. 221-227, 2009.