AL-Rafidain Journal of Computer Sciences and Mathematics

Abstract

In this paper, a system is presented for word recognition using  Arabic word signals. The aim of the paper is to improve the recognition rate by finding out good feature  parameters  based on discrete wavelet transform. We have used Daubechies  wavelet  for the experiment.  The back propagation neural network is used for classification. Test results showing the effectiveness of the proposed system are presented in this paper, A recognition accuracy of 77%.