Optimal neural networks combination for handwritten character recognition

Several methods of combination of Multilayer Perceptrons (MLPs) for handwritten character recognition are presented and discussed. Recognition tests have shown that cooperation of neural networks using different features vectors can reduce significantly the overall misclassification error rate. The final recognition system consists of a cascade association of small MLPs, which allows minimization of the overall recognition time while retaining a high recognition rate. This system appears to be 50% faster than the best of the individual MLPs, while offering a recognition rate of 99.8% on unconstrained digits extracted from the NIST 3 database.