Recognition of Arabic characters using Karhunen-Loeve transform and dynamic programming
Mohamed Fakir, Moha M’Rabet Hassani, Chuichi Sodeyama · 2003
A method for the recognition of Arabic printed characters entered from an image scanner is presented. After the process of smoothing, and midline skew correction, the text is segmented into characters. Then features are extracted using Karhunen-Loeve transform. Next characters are classified using a dynamic programming (DP) technique and the extracted features. The results indicate that the technique offers better classification rate in comparison with existing methods.