Arabic on line characters recognition using improved dynamic Bayesian Networks

Work is in on line Arabic character recognition and the principal motivation is to study the Arab manuscript with on line technology. This system is a Markovien system which one can see as like a Dynamic Bayesian Network (DBN). One of the major interests of these systems resides in the complete models training (topology and parameters) starting from training data. Our approach is based on the dynamic Bayesian Networks formalism. The DBNs theory is a Bayesiens networks generalization to the dynamic processes. Among our objective, amounts finding better parameters which represent the links (dependences) between dynamic network variables. In applications in pattern recognition, one will carry out the fixing structure which obliges us to admit some strong assumptions (for example independence between some variables). Our application will relate to the Arabic isolated characters on line recognition using our laboratory data base: NOUN. A neural tester proposed for DBN external optimization.