Neural Font Style Transfer

Gantugs Atarsaikhan; Brian Kenji Iwana; Atsushi Narusawa; Keiji Yanai; Seiichi Uchida

doi:10.1109/ICDAR.2017.328

Neural Font Style Transfer

Gantugs Atarsaikhan, Brian Kenji Iwana, Atsushi Narusawa, Keiji Yanai, Seiichi Uchida

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

32 Citations (Scopus)

Abstract

In this paper, we chose an approach to generate fonts by using neural style transfer. Neural style transfer uses Convolution Neural Networks(CNN) to transfer the style of one image to another. By modifying neural style transfer, we can achieve neural font style transfer. We also demonstrate the effects of using different weighted factors, character placements, and orientations. In addition, we show the results of using non-Latin alphabets, non-text patterns, and non-text images as style images. Finally, we provide insight into the characteristics of style transfer with fonts.

Original language	English
Title of host publication	Proceedings - 1st Workshop of Machine Learning under International Conference on Document Analysis and Recognition, ICDAR-WML 2017
Publisher	IEEE Computer Society
Pages	51-56
Number of pages	6
ISBN (Electronic)	9781538635865
DOIs	https://doi.org/10.1109/ICDAR.2017.328
Publication status	Published - Jul 2 2017
Event	1st Workshop of Machine Learning under International Conference on Document Analysis and Recognition, ICDAR-WML 2017 - Kyoto, Japan Duration: Nov 11 2017 → …

Publication series

Name	Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
Volume	5
ISSN (Print)	1520-5363

Other

Other	1st Workshop of Machine Learning under International Conference on Document Analysis and Recognition, ICDAR-WML 2017
Country/Territory	Japan
City	Kyoto
Period	11/11/17 → …

All Science Journal Classification (ASJC) codes

Computer Vision and Pattern Recognition

Access to Document

10.1109/ICDAR.2017.328

Cite this

Atarsaikhan, G., Iwana, B. K., Narusawa, A., Yanai, K., & Uchida, S. (2017). Neural Font Style Transfer. In Proceedings - 1st Workshop of Machine Learning under International Conference on Document Analysis and Recognition, ICDAR-WML 2017 (pp. 51-56). (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR; Vol. 5). IEEE Computer Society. https://doi.org/10.1109/ICDAR.2017.328

Neural Font Style Transfer. / Atarsaikhan, Gantugs; Iwana, Brian Kenji; Narusawa, Atsushi et al.
Proceedings - 1st Workshop of Machine Learning under International Conference on Document Analysis and Recognition, ICDAR-WML 2017. IEEE Computer Society, 2017. p. 51-56 (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR; Vol. 5).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Atarsaikhan, G, Iwana, BK, Narusawa, A, Yanai, K & Uchida, S 2017, Neural Font Style Transfer. in Proceedings - 1st Workshop of Machine Learning under International Conference on Document Analysis and Recognition, ICDAR-WML 2017. Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, vol. 5, IEEE Computer Society, pp. 51-56, 1st Workshop of Machine Learning under International Conference on Document Analysis and Recognition, ICDAR-WML 2017, Kyoto, Japan, 11/11/17. https://doi.org/10.1109/ICDAR.2017.328

Atarsaikhan G, Iwana BK, Narusawa A, Yanai K, Uchida S. Neural Font Style Transfer. In Proceedings - 1st Workshop of Machine Learning under International Conference on Document Analysis and Recognition, ICDAR-WML 2017. IEEE Computer Society. 2017. p. 51-56. (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR). doi: 10.1109/ICDAR.2017.328

@inproceedings{f6c20974e67348a79c264e59b65cab0d,

title = "Neural Font Style Transfer",

abstract = "In this paper, we chose an approach to generate fonts by using neural style transfer. Neural style transfer uses Convolution Neural Networks(CNN) to transfer the style of one image to another. By modifying neural style transfer, we can achieve neural font style transfer. We also demonstrate the effects of using different weighted factors, character placements, and orientations. In addition, we show the results of using non-Latin alphabets, non-text patterns, and non-text images as style images. Finally, we provide insight into the characteristics of style transfer with fonts.",

author = "Gantugs Atarsaikhan and Iwana, {Brian Kenji} and Atsushi Narusawa and Keiji Yanai and Seiichi Uchida",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 1st Workshop of Machine Learning under International Conference on Document Analysis and Recognition, ICDAR-WML 2017 ; Conference date: 11-11-2017",

year = "2017",

month = jul,

day = "2",

doi = "10.1109/ICDAR.2017.328",

language = "English",

series = "Proceedings of the International Conference on Document Analysis and Recognition, ICDAR",

publisher = "IEEE Computer Society",

pages = "51--56",

booktitle = "Proceedings - 1st Workshop of Machine Learning under International Conference on Document Analysis and Recognition, ICDAR-WML 2017",

address = "United States",

}

TY - GEN

T1 - Neural Font Style Transfer

AU - Atarsaikhan, Gantugs

AU - Iwana, Brian Kenji

AU - Narusawa, Atsushi

AU - Yanai, Keiji

AU - Uchida, Seiichi

PY - 2017/7/2

Y1 - 2017/7/2

N2 - In this paper, we chose an approach to generate fonts by using neural style transfer. Neural style transfer uses Convolution Neural Networks(CNN) to transfer the style of one image to another. By modifying neural style transfer, we can achieve neural font style transfer. We also demonstrate the effects of using different weighted factors, character placements, and orientations. In addition, we show the results of using non-Latin alphabets, non-text patterns, and non-text images as style images. Finally, we provide insight into the characteristics of style transfer with fonts.

AB - In this paper, we chose an approach to generate fonts by using neural style transfer. Neural style transfer uses Convolution Neural Networks(CNN) to transfer the style of one image to another. By modifying neural style transfer, we can achieve neural font style transfer. We also demonstrate the effects of using different weighted factors, character placements, and orientations. In addition, we show the results of using non-Latin alphabets, non-text patterns, and non-text images as style images. Finally, we provide insight into the characteristics of style transfer with fonts.

UR - http://www.scopus.com/inward/record.url?scp=85045266858&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045266858&partnerID=8YFLogxK

U2 - 10.1109/ICDAR.2017.328

DO - 10.1109/ICDAR.2017.328

M3 - Conference contribution

AN - SCOPUS:85045266858

T3 - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

SP - 51

EP - 56

BT - Proceedings - 1st Workshop of Machine Learning under International Conference on Document Analysis and Recognition, ICDAR-WML 2017

PB - IEEE Computer Society

T2 - 1st Workshop of Machine Learning under International Conference on Document Analysis and Recognition, ICDAR-WML 2017

Y2 - 11 November 2017

ER -

Neural Font Style Transfer

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this