الفهرس | Only 14 pages are availabe for public view |
Abstract During the past -twenty years there has been a considerable ’growth of interest in the problems of pattern recognition. Contributions to the blossom of this area have come from many disciplines, including statistics, psychology, linguistics, computer science, biology, switching theory, communication theory, control theory, and operations research. Many different approaches have been proposed, most of these approaches are dealing with the decision-theoretic (statistical) approach or the syntactic (linguistic) approach. Recognition of handwritten characters is one of the most important fields of the pattern recognition not only because it improves man-machine communication 7 but also because it provides a solution for processing large volumes of data a ut omat i ca I y.Many new research results, both in theory and in application, are continously produced. Most of these, are dealing with Latin characters E1-33, and some with Kanji 14,53, and Korean characters [6]. In this thesis we are dealing with the recognition of isolated handwritten Arabic characters and making use of their special features that differ from the other character sets. A method of recognition and representation of Arabic characters using mixed approach is proposed. It includes the advantages of |