Browse > Article
http://dx.doi.org/10.3745/KTSDE.2021.10.11.473

Few-Shot Korean Font Generation based on Hangul Composability  

Park, Jangkyoung (숭실대학교 컴퓨터공학부)
Ul Hassan, Ammar (숭실대학교 컴퓨터공학부)
Choi, Jaeyoung (숭실대학교 컴퓨터학부)
Publication Information
KIPS Transactions on Software and Data Engineering / v.10, no.11, 2021 , pp. 473-482 More about this Journal
Abstract
Although several Hangul generation models using deep learning have been introduced, they require a lot of data, have a complex structure, requires considerable time and resources, and often fail in style conversion. This paper proposes a model CKFont using the components of the initial, middle, and final components of Hangul as a way to compensate for these problems. The CKFont model is an end-to-end Hangul generation model based on GAN, and it can generate all Hangul in various styles with 28 characters and components of first, middle, and final components of Hangul characters. By acquiring local style information from components, the information is more accurate than global information acquisition, and the result of style conversion improves as it can reduce information loss. This is a model that uses the minimum number of characters among known models, and it is an efficient model that reduces style conversion failures, has a concise structure, and saves time and resources. The concept using components can be used for various image transformations and compositing as well as transformations of other languages.
Keywords
Hangul Font Generation; Font Components; GAN; Few-shot;
Citations & Related Records
연도 인용수 순위
  • Reference
1 J. B. Cha, "Few-shot handwriting copycat AI," DEVIEW 2020 Session, 2020. [Internet] [https://deview.kr/data/deview/session/attach/1400_T4, Jun. 10. 2021.
2 S. Weidman, Deep learning from scratch, O'Reilly Media, Inc. 2019.
3 D. H. Ko, H. Lee, J. Suk, A. U. Hassan, and J. Choi, "Hangul font dataset for Korean font research based on deep learning," KIPS Transactions on Software and Data Engineering, Vol.10, No.2, pp.73-78, 2021.   DOI
4 Y. Gao, Y. Guo, Z. Lian, Y. Tang, and J. Xiao. "Artistic glyph image synthesis via one-stage few-shot learning," Association for Computing Machinery (ACM) Transactions on Graphics, 2019.
5 D.P. Kingma and M. Welling, "Auto-encoding variational bayes," Proceedings of International Conference on Learning Representations, 2014.
6 I. Goodfellow, et al., "Generative adversarial networks," In Advances in Neural Information Processing Systems, ArXiv Preprint arXiv: 1406.2661, 2014.
7 P. Isola, J. Zhu, T. Zhou, and A. A. Efros, "Image-to-image translation with conditional adversarial networks," Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition, (CVPR), 2016.
8 D. Foster, Generative deep learning, O'Reilly Media, Inc. 2020.
9 Y. Tian, "zi2zi: Master chinese calligraphy with conditional adversarial networks," [Internet] https://github.com/kaonashi-tyc/zi2zi, Mar. 22. 2021.
10 J. Cha, S. Chun, G. Lee, B. Lee, S. Kim, and H. Lee, "Few-shot compositional font generation with dual memory," European Conference on Computer Vision (ECCV), 2020.
11 M. Mirza and S. Osindero, "Conditional generative adversarial nets," arXiv preprint arXiv:1411.1784. 2014.
12 Y. Jiang, Z. Lian, Y. Tang, and J. Xiao, "DCFont: An end-toend deep chinese font generation system," SIGGRAPH Asia 2017, Technical Briefs, 2017.
13 G. Parmar, R. Zhang, and J. Y. Zhu, "On buggy resizing libraries and surprising subtleties in FID calculation," 2021, [Internet] https://github.com/bioinf-jku/ TTUR, Sep. 2021.
14 Y. Jiang, Z. Lian, Y. Tang, and J. Xiao, "SCFont: Structure guided Chinese font generation via deep stacked networks," Proceedings of the Association for the Advancement of Artificial Intelligence (AAAI) Conference on Artificial Intelligence, 2019.
15 S. Park, S. Chun, J. Cha, B. Lee, and H. Shim. "Few-shot font generation with localized style representations and factorization," Association for the Advancement of Artificial Intelligence (AAAI), 2021.
16 S. Park , S. Chun, J. Cha, B. Lee, and H. Shim, "Multiple heads are better than one: Few- shot font generation with multiple localized experts," ArXiv abs/2104.00887, 2021.
17 D. H. Ko, A. U. Hassan, J. Suk, and J. Choi, "SKFont: Skeleton-driven Korean font generator with conditional deep adversarial networks," International Journal on Document Analysis and Recognition (IJDAR), 2021.