A novel approach for the recognition of a wide Arabic handwritten word lexicon

This paper introduces a novel approach for the recognition of a wide vocabulary of Arabic handwritten words. Note that there is an essential difference between the global and analytic approaches in pattern recognition. While the global approach is limited to reduced vocabulary, the analytic approach succeeds to recognize a wide vocabulary but meets the problems of word segmentation especially for Arabic. Combining the neural approach with some linguistic characteristics of the Arabic, it is expected that we become able to recognize better and to handle a large vocabulary of Arabic handwritten words. The proposed approach invokes two transparent neural networks, TNN_1 and TNN_2, to respectively recognize roots, schemes and the elements of conjugation from the structural primitives of the words. The approach was evaluated using examples from a database established for this purpose. The results are promising, and suggestions for improvements are proposed.