Arabic Handwritten Word Recognition based on Bernoulli Mixture HMMs

This thesis presents new approaches in off-line Arabic Handwriting Recognition based on conventional Bernoulli Hidden Markov models. Until now, the off-line handwriting recognition, in particular, the Arabic handwriting recognition is still far away form being perfect. Hidden Markov Models (HMMs) are now widely used for off-line handwriting recognition in many languages and, in particular, in Arabic. As in speech recognition, they are usually built from shared, embedded HMMs at symbol level, in which state-conditional probability density functions are modeled with Gaussian mixtures. In contrast to speech recognition, however, it is unclear which kind of features should be used and, indeed, very different features sets are in use today. Among them, we have recently proposed to simply use columns of raw, binary image pixels, which are directly fed into embedded Bernoulli (mixture) HMMs, that is, embedded HMMs in which the emission probabilities are modeled with Bernoulli mixtures. The idea is to by-pass feature extraction and ensure that no discriminative information is filtered out during feature extraction, which in some sense is integrated into the recognition model. In this thesis, we review this idea along with some extensions that are currently providing state-of-the-art results on Arabic handwritten word recognition.