Arabic Handwritten Word Recognition System Based on the Wavelet Packet Decomposition

Abstract

This paper attempts to recognize Arabic handwriting based on the Wavelet Packet Decomposition (WPD) using two different classifiers (Support Vector Machine SVM with three kernels and k-Nearest Neighbors K-NN). The proposed approach of recognizing Arabic handwriting contains three major stages including image preprocessing, extracting the features of the image, and classification. Firstly, the diacritics are removed using the opening morphological operation (i.e image preprocessing). Secondly, extracting the structure of the paragraph using the morphological method. Finally, the word image size is converted into a suitable size for the next stages. To extract features from the image, the WPD method was adopted to extract the features of Arabic handwriting as the transformation method of feature space. This extracts the Arabic global features to be classified in the last stage using the SVM with polynomial kernel and K-NN. The proposed approach of recognizing Arabic handwriting was tested on IFN/ENIT dataset by rescaling images into various sizes, 93.7% when the SVM with polynomial kernel is used, K-NN classifier achieved accuracy rate is 88.4%.