Incremental learning for feature extraction filter mask used in similar pattern classification

The incremental learning system for a feature extraction unit in the character recognition system is described and experimental results are shown. The relationship between this learning system and neural networks (NN) are explained and the specifications of this method are described as an NN application. The improved version of this system which is related to the Gabor filter was tested and an accuracy improvement was shown in the experiments of a similar pattern classification. An important goal of this research was to observe created filter masks. It was confirmed that the visual pattern of created filter masks was reasonable for the purpose.