No abstract

No abstract

We describe a practical implementation of a Radial Basis Function Network for handwritten digits recognition. Inspired from regularization theory and Parzen windows non parametric estimator, Radial Basis Function networks are testedfor a classification task. Reduction of the number of hidden nodes which is an important and necessary step to obtain a computationally tractable network is ma& using an original technique. A comparison is ma& with the k-nearest neighbour meihod. Results appear better for the network at a much lower computational cost.

No abstract

We describe an implemented system which reads amounts on French checks images. This system is made of two modules which recognize independently the courtesy and the legal amount. The first one is based on a segmentation-by-recognition approach while the second uses hidden Markov models of words. The outputs of these two modules are combined into a system decision. A high reliability is achieved through this combination since the errors made by the recognition modules should be mostly uncorrelated.