earticle

영어

Recognition of Arabic handwriting characters is a dicult task due to similar appearance of some dierent characters. However, the selection of the method for feature extraction remains the most important step for achieving high recognition accuracy. The purpose of this paper is to compare the eectiveness of Discrete Cosine Transform and Discrete Wavelet transform to capture discriminative features of Arabic handwritten characters. A new database containing 5600 characters covering all shapes of Arabic handwriting charac-ters has also developed for the purpose of the analysis. The coecients of both techniques have been used for classication based on a Articial Neural Network implementation. The results have been analysed and the nding have demonstrated that a Discrete Cosine Trans-form based feature extraction yields a superior recognition than its counterpart.