Region-mapping neural network model for pattern recognition
Yanlai Li, Kuanquan Wang, David D. Zhang · 2003
In general, the process for multilayer feedforward neural network in pattern recognition is composed of two phases: training and classifying. The aim of the training phase is to make it possible for the network output to meet the desired output given by the training patterns. It demands a map of point to point, which is so strict that it often causes the criterion inconsistence between training and classifying. Consequently, the recognition rate would be decreased. The region-mapping model has changed the output space from one point to a certain supervisor region so that it has overcome the shortcoming of the inconsistent problem between training and testing as a common multilayer perceptron (MLP) does. Furthermore, it can save much of the computing time by mapping the input data to an output area rather than an output point. This paper presents a region-mapping model with quarter hyper globe as a supervisor region. The gradient decent algorithm is applied to this model. In order to illustrate the effect of our propounded model, a handwritten letter recognition problem was carried out in an experiment. Moment invariant features are used as input parameters. The simulation results show that the region-mapping model has much better characteristics than those common multiplayer perceptrons. Also, the quarter hyper globe rule is more reasonable than the hypercube one.