المستخلص: |
Arabic characters are widely used in Arabic speaking countries as well as in languages such as Persian and Urdu. However, little work has been done on the recognition of Arabic characters. This paper proposes a new method for the recognition of machine printed Arabic characters. The proposed method employs Ishii et al's chaotic neural network model, which is called globally coupled map using the symmetric map (S- GCM), for recognizing Arabic characters. The proposed method is tested on two fonts, Simplified Arabic and Arabic Transparent, and 9 sizes, 8, 9, 10, 11, 12, 14, 16, 18, 20. The recognition rate is over 97%.
|