Amazigh Character Recognition System Based on Continuous HMMs and Directional Features

This paper proposes a global approach to the recognition of handwritten Amazigh characters. The method used is based on continuous Hidden Markov Models and directional features. The input provided to our system is a vector of features extracted directly from an image of Amazigh characters using sliding windows technique based on hough transform. The obtained vector is translated into a sequence of observations that is used for the learning phase. This task involves several of processing steps, typically, pre-processing, normalization, skeletonization and features extraction. Finally the class of the input characters is determined by the Viterbi classifier. The experimental result indicates the promising prospect