Ancient Character Image Classification Model Training

Nowadays, various neural network models are updated, and most industries around the world need deep learning algorithms to solve a lot of practical problems. In this paper, we propose the task of image recognition of ancient Chinese characters based on RESNET network model, in order to provide help for students to learn ancient Chinese characters. In the work, the classification of five ancient Chinese characters is completed. The results of RESNET network model are very good, and the accuracy of the final result of the test set is 90%. At the same time, the stability of the model was tested after training, including vertical and horizontal flipping of the image of the test set, and adding noise to the image of the test set. Finally, the RESNET network model is summarized and its applicable environment is described.