Abstract: In this study, we present an off line method of handwritten isolated digits Recognition. The study is based on the analysis and the evaluation of multi-layers perceptron performances, trained with the gradient back propagation algorithm. It is hoped that the results of the evaluation contribute to the conception of operational systems. The used parameters to form the input vector of the neural network are extracted on the binary images of the digits by two methods: the centred moments of the distribution sequences and the Barr features