—In this work, we propose a novel system for the recognition of handwritten Arabic words. It is evolved based on horizontal-vertical Hidden Markov Model and Dynamic Bayesian Network Model. Our strategy consists of looking for various HMM architectures and selecting those which provide the best recognition performance. Experiments on handwritten Arabic words from IFN/ENIT strongly support the feasibility of the proposed approach. The recognition rates achieve 92.19% with horizontal-vertical Hidden Markov Model and 88.82% with a Dynamic Bayesian Network.