Recognizing Characters Based on Gaussian-Hermite Moments and BP Neural Networks

Moments are widely used in pattern recognition, image processing, computer vision and multi resolution analysis. In this paper, we first printout Gaussian-Hermite moments, and propose a new method to extract the character features based on Gaussian-Hermite moments. Following, for training network, the moment features were inputted to BP network as the parameters; so that, a classifier was realized for recognizing the character image. The experiment results are reported also, which show the good performance of our method.