An Active Shape Model based approach for Arabic handwritten character recognition

A lot of research has been conducted in order to solve the problem of unconstrained Arabic handwriting recognition. Nonetheless, an effective solution is still a serious challenge. In this paper, we propose an new Active Shape Model (ASM) based approach for recognition of Arabic handwritten text. Character candidate representations are generated using chamfer distance transforms, and optimal parameters for ASMs are calculated. Furthermore, a performance comparison among three different optimization techniques, is presented. For experiments, we used 28046 letter samples from different writers. Two third to build the ASMs and one third for testing. Results were satisfactory, and we showed that our approach is a promising and a step forward in the field.