Abstract: This study addresses a segmentation technique to handwritten word recognition. This technique implements an algorithm based on analytical approach. It uses a letter sweeping procedure with a step equal to the Euclidian distance between an established reference index and the entity (the alphabet letters). Then a dissociation of this entity is achieved when this distance reached a rate of 80%. Experimenting our segmentation technique gives a rate of 81.05% of recognition whole. A neuronal multi-layer perceptron classifier confirms the extracted segment. This procedure is successively repeated from the beginning until the end of the word. A concatenation is finally used to the word reconstitution.