Comparison of feed-forward neural net algorithms in application to character recognition

In a neural network based character recognition system it is important to choose a training algorithm with high generalization ability. In this paper, we apply three different multilayer feedforward training algorithms namely, backpropagation, double backpropagation and weight smoothing algorithm in a neural network based invariant character recognition model. The model consists of a preprocessor and a classifier. The preprocessor extracts geometrical features of the input character and passes the feature values through a rapid transform block which performs a cyclic shift invariant transform on its input. The classifier is a neural network classifier. Simulation results with 26 English capital letters show that the recognition system achieves best performance with significantly high recognition rate when trained with weight smoothing learning algorithm.