The algorithm and implementation of Yi character recognition based on convolutional neural network

Yi characters have unique historical value and rich cultural connotations, but the classification and recognition of Yi characters started late and the research is not deep enough. In this paper, a character recognition DCNN (Deep Convolutional Neural Network) based on DL (Deep Learning) is designed. Compared with traditional printed Yi characters recognition algorithms such as structural pattern recognition and artificial neural network, it has some shortcomings such as low accuracy and poor robustness, which not only improves the accuracy of Yi characters recognition, but also has a higher recognition rate for Chinese characters with noises. After testing, the accuracy of DCNN on training data set and test data set is as high as 0.95, which shows that the neural network model can perfectly fit the training set of Yi character recognition.