A method for generating various style Chinese fonts in the absence of training data (S)
Kang Shi · Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering · 2021
In recent years, the generation of arbitrary style fonts has drawn broad attention.At present, the common idea of most methods is to train the model through a large number of text samples of a specific style, so that the model can learn the font style, and then automatically generate all the text of the style.However, in the case of insufficient sample data, almost all the current methods fail.In this paper, we investigate how to generate arbitrary style Chinese fonts automatically, especially when the sample data of specific style is insufficient.In order to solve the problem, we propose a new frame.The method can be used to generate the fonts of Chinese ancient calligraphers whose relics are rare.The experimental results show the effectiveness of the new frame.