PCA-based Arabic Character feature extraction

In this paper we propose two level recognition processes for Arabic characters. Arabic fonts are connected in nature and thus require segmentation for recognition. Document images are segmented into lines, words or subwords and then characters. In the proposed approach, recognition is applied at two levels with different strategies. First level recognition is applied after dasiawordspsila segmentation to recognize isolated characters while second level recognition is applied to segmented characters. The proposed scheme is tested on different font systems which yielded a recognition rate of about 90%.