当前位置: X-MOL 学术IEEE Comput. Graph. Appl. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Automatic Generation of Typographic Font from Small Font Subset
IEEE Computer Graphics and Applications ( IF 1.7 ) Pub Date : 2020-01-01 , DOI: 10.1109/mcg.2019.2931431
Tomo Miyazaki 1 , Tatsunori Tsuchiya 1 , Yoshihiro Sugaya 1 , Shinichiro Omachi 1 , Masakazu Iwamura 2 , Seiichi Uchida 3 , Koichi Kise 2
Affiliation  

The automated generation of fonts containing a large number of characters is in high demand. For example, a typical Japanese font requires over 1000 characters. Unfortunately, professional typographers create the majority of fonts, resulting in significant financial and time investments for font generation. The main contribution of this article is the development of a method that automatically generates a target typographic font containing thousands of characters, from a small subset of character images in the target font. We generate characters other than the subset so that a complete font is obtained. We propose a novel font generation method with the capability to deal with various fonts, including a font composed of distinctive strokes, which are difficult for existing methods to handle. We demonstrated the proposed method by generating 2965 characters in 47 fonts. Moreover, objective and subjective evaluations verified that the generated characters are similar to the original characters.

中文翻译:

从小字体子集自动生成排版字体

自动生成包含大量字符的字体的需求量很大。例如,典型的日语字体需要超过 1000 个字符。不幸的是,大多数字体都是由专业排版师创建的,因此需要在字体生成方面投入大量资金和时间。本文的主要贡献是开发了一种方法,该方法可以从目标字体中的一小部分字符图像自动生成包含数千个字符的目标印刷字体。我们生成子集以外的字符,以便获得完整的字体。我们提出了一种新颖的字体生成方法,能够处理各种字体,包括由现有方法难以处理的独特笔画组成的字体。我们通过生成 47 种字体的 2965 个字符来演示所提出的方法。此外,客观和主观评估验证了生成的字符与原始字符相似。
更新日期:2020-01-01
down
wechat
bug