Adaptive OCR Technique for Arabic Characters

Abstract

AbstractOCR is an artificial intelligence, recognition English characters have been solved by a huge number of studies last 3 decades, but Arabic letters which used by at least one billion people have not been definitively resolved yet, therefore In this study proposes an effective approach to the recognition of off-line of 121 Arabic characters which is involves of creating database (DB), contains standard image for 59 main character target and Characters Indexing Table (CIT), contains indices of 62 main character target to be used in recognition process. The (DB) is designed to identify the main body of the 59 unknown characters. The (CIT) is responsible of identifying the secondary components, the number of dots or hamza that is associated with the body of character and their position. The mean square error classifier (MSE) is used in the recognition stage, where each character is assigned the best 6 matches with the lowest MSE. The lowest MSE value is 0.025 and the highest value is 0.09.