A Mlp-Based Digit And Uppercase Characters Recognition System
A simple software solution for digit and uppercase handwritten characters recognition is presented. The proposed solution is based on a two-layer Multi Layer Perceptron (MLP) trained by a conjugate gradient descent (CGD) optimization algorithm. This neural network is embedded in a software tool for automatic processing of forms achieved using a scanner. The chosen solutions allow us to obtain good results both in terms of recognition rate and speed. In the paper are fully described design details and experimental results.
Unable to display preview. Download preview PDF.
- G. A. M. Gioiello, F. Sorbello, A. Tarantino, G. Vassallo, Simple Techniques for an Efficient Recognition of Handwritten Characters using a MLP, submitted to International Journal of Intelligence Systems.Google Scholar
- G. A. M. Gioiello, F. Sorbello, A. Tarantino, G. Vassallo, A neural solution for the hand-written character recognition task using a MLP digital architecture, Twelfth LASTED International Conference February 20–23 1995, Innsbruck, Austria.Google Scholar
- M. J. D. Powell, Restart Procedures for the Conjugate Gradient Method, Mathematical Programming, Vol. 12, pp. 241–254.Google Scholar
- G. Vassallo, G. A. M. Gioiello, C. Condemi, F. Sorbello, A MLP-Based character recognition system, Proc. of the International Conference On Artificial Neural Networks, ICANN’94, Sorrento, Italy, 26–29 May, 1994. Springer Verlag edsGoogle Scholar