Study On Chinese Character Recognition System Based On Neural Network Classifier

Chinese character recognition (CCR) is a typical large vocabulary pattern recognition problem. In the research of large vocabulary recognition, matching approaches are frequently adopted because it is easy to be realized. But the classification performance of matching approaches is not good. In recent years artificial neural network (ANN) has been successfully applied into pattern recognition. After analyzing the currently up-to-date techniques for Chinese character recognition, in this paper, we propose Chinese Character Recognition method based on Neural Network classifier.In this paper, first, the modules in the system are explained in detail including the input of Chinese character, preprocessing, feature extraction and BP neural network classifier, we propose the feature extraction method based on Statistics amount of periphery feature and meshing feature, and then a BP neural network classifier is used for Chinese Character recognition. Especially as to the neural network classifier, we not only discuss the fundamental principle of BP network, the realization of BP network, the selection of network structure and parameters, but also discuss its drawbacks and its improved solutions.Lastly, in VC++ 6.0 environment, we realize the program of creating BP network and training BP network, and choice samples of 10 categories of handwritten Chinese characters produced the result of recognition, showing that using neural network for CCR is feasible and promising.