Chinese Character Style Transfer Model Based on Convolutional Neural Network

With various styles, Chinese characters are one of the most important cultural symbols in China. Designing a set of new fonts with a specific style is a very tedious and massive task. It usually relies on traditional manual methods or computer-aided design for each Chinese character, which is time-consuming and labor-intensive. And the products are often not ideal. Therefore, it is necessary to design a model that can automatically generate new Chinese characters in a specified style. In this paper, a convolutional neural network model is proposed to be applied into the Chinese character style migration. To train the network, we exploit the root mean square optimizer to automatically adjust the deep learning rate and gradually reduce the difference values. Experiments are conducted based on the Chinese character datasets. Ultimately the resulting character style is basically close to the manually designed one, which reaches the target of the font style transfer.