Abstract
Arabic text recognition offers unique technical challenges and has been addressed more recently in the document analysis research field than other languages. Automatic Arabic/Indian numeral Optical Character Recognition (OCR) system for postal services are used in many countries, but still there are problems in such systems where machines still provide errors in reading the crucial information needed to distribute the mail efficiently. The need to investigate fast and efficient recognition methods is important so as to correctly read the postal codes from mail envelopes. The significance of this study is to recognize essential information, e.g., postal codes from the mail envelopes, by applying the OCR methods. The proposed system is a hybrid of three different feature extraction methods and classification methods. The proposed system, systematically compares the performance of each and every method, and makes sure that the numeral is recognized or rejected. The results provide a recognition rate of 99.4%.