Fast Technique to Recognize Closed Characters in Arabic Handwriting

Abstract

Considering the distinctive features and characteristics of Arabic scripts,recognizing handwritten Arabic characters is still widely open as a majorexperimental task, which is not easy to overcome. This study attempts to developa fast and effective technique for recognizing this difficult type of written scriptby using an iterative algorithm to extract closed Arabic characters. Some Arabiccharacters have circles that may be blurred, incomplete, unformed, or distorted. Inaddition to ligatures with different shapes, the technique is based on thedevelopment of a proper Circular Hough Transform. This study used IFN/ENIT,which is a standard database for extracting closed Arabic characters as designedin classes. The first class is closed blurred circles ( .)ق, م , ع ,وThe second class isunformed circles ( .)ق, ع , ةThe third one is incomplete circles (ط , ظ, ص, ض, .)ه,ةFinally, the fourth class is distorted circles ( .) ط, ظThis methodologyachieved an outstanding accuracy of approximately 96.67%, a very interestingwork for the total four classes related to the 11 closed Arabic characters (out ofthe 28 characters of the Arabic alphabet)..