Automatic Generation of Typographic Font from Small Font Subset

Tomo Miyazaki, Tatsunori Tsuchiya, Yoshihiro Sugaya, Shinichiro Omachi, Masakazu Iwamura, Seiichi Uchida, Koichi Kise

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

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.

Original languageEnglish
Article number8782647
Pages (from-to)99-111
Number of pages13
JournalIEEE Computer Graphics and Applications
Volume40
Issue number1
DOIs
Publication statusPublished - Jan 1 2020

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Graphics and Computer-Aided Design

Cite this

Miyazaki, T., Tsuchiya, T., Sugaya, Y., Omachi, S., Iwamura, M., Uchida, S., & Kise, K. (2020). Automatic Generation of Typographic Font from Small Font Subset. IEEE Computer Graphics and Applications, 40(1), 99-111. [8782647]. https://doi.org/10.1109/MCG.2019.2931431

Automatic Generation of Typographic Font from Small Font Subset. / Miyazaki, Tomo; Tsuchiya, Tatsunori; Sugaya, Yoshihiro; Omachi, Shinichiro; Iwamura, Masakazu; Uchida, Seiichi; Kise, Koichi.

In: IEEE Computer Graphics and Applications, Vol. 40, No. 1, 8782647, 01.01.2020, p. 99-111.

Research output: Contribution to journalArticle

Miyazaki, T, Tsuchiya, T, Sugaya, Y, Omachi, S, Iwamura, M, Uchida, S & Kise, K 2020, 'Automatic Generation of Typographic Font from Small Font Subset', IEEE Computer Graphics and Applications, vol. 40, no. 1, 8782647, pp. 99-111. https://doi.org/10.1109/MCG.2019.2931431
Miyazaki, Tomo ; Tsuchiya, Tatsunori ; Sugaya, Yoshihiro ; Omachi, Shinichiro ; Iwamura, Masakazu ; Uchida, Seiichi ; Kise, Koichi. / Automatic Generation of Typographic Font from Small Font Subset. In: IEEE Computer Graphics and Applications. 2020 ; Vol. 40, No. 1. pp. 99-111.
@article{effdd3a4795c4c85bd662482efb46e05,
title = "Automatic Generation of Typographic Font from Small Font Subset",
abstract = "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.",
author = "Tomo Miyazaki and Tatsunori Tsuchiya and Yoshihiro Sugaya and Shinichiro Omachi and Masakazu Iwamura and Seiichi Uchida and Koichi Kise",
year = "2020",
month = "1",
day = "1",
doi = "10.1109/MCG.2019.2931431",
language = "English",
volume = "40",
pages = "99--111",
journal = "IEEE Computer Graphics and Applications",
issn = "0272-1716",
publisher = "IEEE Computer Society",
number = "1",

}

TY - JOUR

T1 - Automatic Generation of Typographic Font from Small Font Subset

AU - Miyazaki, Tomo

AU - Tsuchiya, Tatsunori

AU - Sugaya, Yoshihiro

AU - Omachi, Shinichiro

AU - Iwamura, Masakazu

AU - Uchida, Seiichi

AU - Kise, Koichi

PY - 2020/1/1

Y1 - 2020/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85070355502&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070355502&partnerID=8YFLogxK

U2 - 10.1109/MCG.2019.2931431

DO - 10.1109/MCG.2019.2931431

M3 - Article

AN - SCOPUS:85070355502

VL - 40

SP - 99

EP - 111

JO - IEEE Computer Graphics and Applications

JF - IEEE Computer Graphics and Applications

SN - 0272-1716

IS - 1

M1 - 8782647

ER -