Krawtchouk moment feature extraction for neural Arabic handwritten words recognition

This paper proposes a new approach investigating the application of Krawtchouk moment method to evaluate a set of candidate features and to select an informative subset to be used as input data for a neural network classifier. The first step (pre-processing) of the proposed method takes into account the discriminative properties of invariant Krawtchouk moments. The second step (recognition) is achieved by using Multilayer Feedforward Neural Network (MFNN) as a classifier with the stochastic back propagation as a learning algorithm. Finite vectors obtained as a result in the pre-processing phase are then fed into the neural network system. We demonstrate experimentally that the choice of a Krawtchouk moment subset which contains sufficient and discriminative information about the input pattern is crucial in the convergence of the neural network training algorithm to a satisfactory performance level. The proposed method has been tested on the well known IFN/ENIT database of Arabic handwritten words. It produces excellent and encouraging results by reducing the computational burden of the recognition system and presenting a high recognition rate with a good generalization ability.This electronic document is a ldquoliverdquo template. The various components of your paper [title, text, heads, etc.] are already defined on the style sheet, as illustrated by the portions given in this document.