Font Style Transfer Using Neural Style Transfer and Unsupervised Cross-domain Transfer
Font Style Transfer Using Neural Style Transfer and Unsupervised Cross-domain Transfer
复制标题
DOI：
10.1007/978-3-030-21074-8_9
复制
发表时间：
2018-12
期刊：
影响因子：
--
通讯作者：
Atsushi Narusawa;Wataru Shimoda;Keiji Yanai
中科院分区：
文献类型：
--
作者：
Atsushi Narusawa;Wataru Shimoda;Keiji Yanai
本文主要研究字体的生成和转换。以前的方法把字符看作是由笔画组成的字符。相反，我们使用深度学习从字体图像和纹理或图案图像中提取相当于笔画的特征，并转换字体图像的设计模式。我们期望，生成原始字体，如手写字符将自动生成所提出的方法。在实验中，我们创建了独特的数据集，如番茄酱字符图像数据集，并通过将神经风格转移与无监督跨域学习相结合来提高图像生成质量和字符的可读性。
In this paper, we study about font generation and conversion. The previous methods dealt with characters as ones made of strokes. On the contrary, we extract features, which are equivalent to the strokes, from font images and texture or pattern images using deep learning, and transform the design pattern of font images. We expect that generation of original font such as hand written characters will be generated automatically by the proposed approach. In the experiments, we have created unique datasets such as a ketchup character image dataset and improve image generation quality and readability of character by combining neural style transfer with unsupervised cross-domain learning.