基于生成式对抗网络的中文字体风格迁移

Chinese fonts style transfer based on generative adversarial networks

风格多样的中文字体是一种重要的中国文化符号,它的设计和操作是一项需要大量专业知识的艰巨工作。因此,针对这项工作提出一种基于生成式对抗网络的中文字体风格迁移的新方法。实验中,使用基于残差网络结构的生成式模型,在均方误差约束下,进行生成式模型与判别式模型之间的对抗训练,最后使用训练所得的生成式模型实现不同中文字体间一对一和多对多的风格迁移。实验表明,与之前常用的基于l1正则化方法相比,使用这种方法在字体细节生成上有更出色的表现,简化了中文字体的建模方式,提高了生成图像的逼真度,并具有更好的灵活性和通用性。

A variety of Chinese characters is an important Chinese cultural symbol.Its design and operation are a hard work requiring a lot of professional knowledge.Therefore,for this work,this paper proposed a new method of Chinese fonts style transfer based on generative adversarial networks.In the experiment,it used a generative model based on the residual network structure and performed the adversarial training between the generative model and the discriminative model under the constraint of mean square error.At last,the trained generative model could be used to implement one-to-one and many-to-many style transfer between different Chinese fonts.Experiments show that,compared with the usual l 1 regularization method used before,the method in this paper has better performance in fonts detail generation,simplifies Chinese fonts modeling,improves the fidelity of generated images,and has better flexibility and versatility.