Abstract :
Arabic characters are widely used in Arabic countries. However, there is a little work has been done on recognition of Arabic characters. This paper proposed a new method for recognition 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 greater than 97%
Keywords :
character recognition; character sets; image recognition; natural languages; neural nets; Arabic Transparent; Simplified Arabic; chaotic neural network model; globally coupled map using the symmetric map; machine printed Arabic character recognition; Artificial neural networks; Cellular neural networks; Chaos; Character recognition; Classification tree analysis; Computer science; Natural languages; Neural networks; Testing; Vocabulary;
