To search, Click below search items.


All Published Papers Search Service


Krawtchouk Moment Feature Extraction for Neural Arabic Handwritten Words Recognition


Anass El affar, Khalid Ferdous, Abdeljabbar Cherkaoui, Hakim El fadili, Hassan Qjidaa


Vol. 9  No. 1  pp. 417-423


This paper proposes a new approach investigating the application of 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 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 kratchouk 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 result by reducing the computational burden of the recognition system and presenting a high recognition rate with good generalization ability.


Method of moments, invariant krawtchouk moments, multilayer feedforward neural network, Arabic handwritten recognition