Design and implementation of handwritten Chinese character recognition method based on CNN and TensorFlow

Abstract

Chinese characters are an important medium for Chinese people to exchange information and perceive the world. With the advent of the information age, a large number of paper documents need to be electronically stored and shared. The recognition accuracy of paper printed Chinese characters and online handwritten Chinese characters has reached a high level. However, offline handwritten Chinese characters have a variety of styles and shapes. There is still a lot of room for improvement in the current recognition accuracy due to a large number of similar characters. This work proposes a "private customized" handwritten Chinese character recognition system based on convolutional neural networks. Users can train their neural network model according to their own writing style. The system includes four parts: character segmentation, Chinese character labeling, neural network training, and predictive recognition. The system can independently expand the data set during use, thereby continuously improving the recognition accuracy. The experimental results show that this method has a good recognition effect for Chinese characters, English letters, Arabic numerals, and punctuation marks, and the recognition accuracy rate can reach more than 98%.