A Chinese Font Generation Method based on Dynamic Convolution Improved Generative Adversarial Network

Font generation is a challenging research topic in the field of computer vision, aiming to apply the style from a reference image to a source character image. The core task of font generation is to generate images, especially complex character images, that closely resemble the style of the reference font while maintaining the original glyph structure. This paper proposes a novel font generation method based on the generation adversarial network (GAN). Firstly, a new unsupervised end-to-end Chinese font generation network is designed. Then, a Convolution-Transformer (CNNTrans) module is devised to extract style features from global and local with attention constraint. Finally, a dynamic convolutional skip connection module (DCSC) is proposed to dynamically fuse font content and style according the importance of content and style features in different positions. Experimental results demonstrate that the proposed font generation method can generate higher quality styled fonts compared to other methods.

I. Introduction

The font generation method based on image translation is designed to convert the font image from the source domain to the target domain to generate new font characters based on the reference character image, which can greatly reduce the workload of professional designers to create new font styles [1] [2]. Traditional font design relies heavily on expert designers to manually customize the glyph and style of each character, which makes the task of font design extremely labor-intensive. The application of automatic font generation technology to generate target fonts will greatly save human resources, promote innovative expression of art, and promote the protection of cultural heritage.