caa a22 4500 477034403 CHVBK 20180405111301.0 cr unu---uuuuu 170330e19960401xx s 000 0 eng 10.1007/BF00417783 doi (NATIONALLICENCE)springer-10.1007/BF00417783 Gosselin Bernard Circuit Theory & Signal Processing Laboratory, Faculté Polytechnique de Mons, Bd Dolez 31, B-7000, Mons, Belgium aut Multilayer perceptrons combination applied to handwritten character recognition [Elektronische Daten] [Bernard Gosselin] 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. Additionally, the MLPs that are combined are the results of the experiments that were previously performed in order to optimize the recognition process when using a single MLP. So, all the combination methods that are proposed are very easy to carry out. 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 2.5 times 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. Kluwer Academic Publishers, 1996 features extraction nationallicence multilayer perceptron nationallicence optical character recogniton nationallicence Neural Processing Letters Kluwer Academic Publishers; http://www.wkap.nl 3/1(1996-04-01), 3-10 1370-4621 3:1<3 1996 3 11063 https://doi.org/10.1007/BF00417783 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/BF00417783 text/html Onlinezugriff via DOI NATIONALLICENCE 100 1- Gosselin Bernard Circuit Theory & Signal Processing Laboratory, Faculté Polytechnique de Mons, Bd Dolez 31, B-7000, Mons, Belgium aut NATIONALLICENCE 773 0- Neural Processing Letters Kluwer Academic Publishers; http://www.wkap.nl 3/1(1996-04-01), 3-10 1370-4621 3:1<3 1996 3 11063 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer