Preprocessing for handwritten Chinese character based on neural networks

Introduces the entropy concept to a backpropagation neural network in order to improve its performance of classifying similar samples. Then, based on the neural network, we propose a thinning model for Chinese characters, and state its preprocessing methods, neural network architecture, learning algorithm and working algorithm. At the same time, we reform the conventional thinning process for Chinese characters in order to improve speed of processing. Finally, combining the nonlinear shape normalization methods and the reformed thinning process, an experiment on handwritten Chinese character preprocessing has been done to test the model, and obtain satisfactory results