The Use of Object-Oriented Approach for Arabic Documents Recognition
Ibrahim Albidewi, Saudi Arabia · 2008
This paper presents a system for Arabic character recognition which is implemented using Object Oriented Programming (OOP). The system starts by scanning the document which will be processed to resolve the skewing problem, and then the document will be segmented into lines where each is segmented into words. Each word is segmented into characters or primitives also some characters will be fragmented during this process. The features of the fragments characters will be obtained and a neural network module will be used for the recognition. A finite state automata recognizer is used for recognizing the fragments of each character. Key words: