Gaussian Synapse Networks for Handwritten Character Recognition
In the context of improved higher order neural architectures for pattern recognition we have made use of a new type of higher order network containing gaussian synapses and developed the Gaussian Synapses Backpropagation Algorithm (GSBP) for the implementation of different types of pattern detectors. This paper concentrates on the presentation of the algorithm and its comparison to other structures in a typical benchmark problem i.e. the recognition of handwritten characters. The inclusion of gaussian functions in the synapses of the network allows the training algorithm to select the appropriate spatial information and filter out all that is irrelevant according to the training it has received. With this strategy it is possible to obtain very good recognition results with hardly any preprocessing and independently of backgrounds and slant using small networks that are quite easy to train.
KeywordsOptical Character Recognition Handwriting Recognition Handwritten Character Curve Network Handwritten Character Recognition
Unable to display preview. Download preview PDF.
- Duro, R.J., Crespo, J.L., and Santos, J.: Training Higher Order Gaussian Synapses. Lecture Notes in Computer Science, Vol 1606 Springer-Verlag, Berlin (1999) 537–545.Google Scholar
- Suen C.Y., Nadal, C., Legault, R, May, T. A. and Lam, L.: Computer Recognition of Handwritten Numerals, Proc IEEE, V80, (1992),1162–1180.Google Scholar
- Shustorovich, A. and Thrasher, C. W.:Neural Network Positioning and Classification of Handwritten Characters, Neural Networks, V9, N4, (1996), 685–693.Google Scholar