Advanced Neural Networks Methods for Recognition of Handwritten Characters
In this paper, we present the efficient voting classifier for the recognition of handwritten characters. This system consists of three voting nonlinear classifiers: two of them base on the multilayer perceptron, and one uses the moments method. The combination of these kinds of systems showed superiority of neural techniques applied with classical against exclusive traditional approach and resulted in high percentage of correctly recognized characters. Also, we present a comparison of the recognition results.
KeywordsFeature Vector Character Recognition Multilayer Perceptron Moment Method Handwritten Character
Unable to display preview. Download preview PDF.
- Y. Le Cun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel, “Handwritten Digit Recognition with a Back-Propagation Network,” in Advances in Neural Information Processing Systems 2 (D. S. Touretzky, ed.), pp. 396–404, San Mateo, CA: Kaufmann, 1990.Google Scholar
- S. Skoneczny, R. Foltyniewicz, and J. Szostakowski, “Neural Network Based Classifiers as Useful Tools in Zip Code Recognition Task,” in Proc. NOLTA’93, vol. 3, (Hawaii, USA), pp. 941–944, December 1993.Google Scholar