Recognition of Printed Arabic Script Using Support Vector Machine

Abstract

Arabic Optical Character Recognition (AOCR) is the science of conversion Arabic text image documents of type printed, or handwritten into editable text. OCR role is to help or replace humans in computerizing paperwork in order to accelerate, improve and reduce cost as well as time and effort. It provide although the ability to electronically editing, storing more compactly and searching documents. It is not a recent research field; it had started about 40 years ago. The need for it has become increasingly urgent due to overcrowding paperwork in our societies. So a lot of research conducted on AOCR as the Arabic script language is the mother language of over quarter of the world population despite this fact, robust and reliable performance AOCR system is still challenge. In this thesis, a proposed Arabic Character dataset generated for evaluating and testing feature extraction systems purpose. a combination of statistical features has been proposed to increase the recognition accuracy, using SVM classifier. For text recognition, a novel segmentation approach for machine Arabic printed text for different segmentation stages; line segmentation, word and sub-word segmentation, and character segmentation based on profile projection techniques are proposed.