DOI QR코드

DOI QR Code

Few-Shot Korean Font Generation based on Hangul Composability

한글 조합성에 기반한 최소 글자를 사용하는 한글 폰트 생성 모델

  • Received : 2021.09.30
  • Accepted : 2021.10.11
  • Published : 2021.11.30

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.

최근 딥러닝을 이용한 한글 생성 모델이 연구되고 있으나, 한글 폰트의 구조가 복잡하고 많은 폰트 데이터가 필요하여 상당한 시간과 자원을 필요로 할 뿐 아니라 스타일이 제대로 변환되지 않는 경우도 발생한다. 이러한 문제점을 보완하기 위하여, 본 논문에서는 한글의 초성, 중성, 종성의 구성요소를 기반으로 최소 글자를 사용하는 한글 폰트 생성 모델인 CKFont 모델을 제안한다. CKFont 모델은 GAN을 사용하는 한글 자동 생성 모델로, 28개의 글자와 초/중/종성 구성요소를 이용하여 다양한 스타일의 모든 한글을 생성할 수 있다. 구성요소로부터 로컬 스타일 정보를 획득함으로써, 글로벌 정보 획득보다 정확하고 정보 손실을 줄일 수 있다. 실험 결과 스타일을 자연스럽게 변환되지 못하는 경우를 감소시키고 폰트의 품질이 향상되었다. 한글 폰트를 생성하는 다른 모델들과 비교하여, 본 연구에서 제안하는 CKFont는 최소 글자를 사용하는 모델로, 모델의 구조가 간결하여 폰트를 생성하는 시간과 자원이 절약되는 효율적인 모델이다. 구성요소를 이용하는 방법은 다른 언어 폰트의 변환은 물론 다양한 이미지 변환과 합성에도 사용될 수 있다.

Keywords

Acknowledgement

이 논문은 2021년도 정부(과학기술정보통신부)의 재원으로 정보통신기획평가원의 지원을 받아 수행된 연구임(No. 2016-0-00166).

References

  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. I. Goodfellow, et al., "Generative adversarial networks," In Advances in Neural Information Processing Systems, ArXiv Preprint arXiv: 1406.2661, 2014.
  3. 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.
  4. S. Weidman, Deep learning from scratch, O'Reilly Media, Inc. 2019.
  5. D. Foster, Generative deep learning, O'Reilly Media, Inc. 2020.
  6. Y. Tian, "zi2zi: Master chinese calligraphy with conditional adversarial networks," [Internet] https://github.com/kaonashi-tyc/zi2zi, Mar. 22. 2021.
  7. 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.
  8. 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.
  9. M. Mirza and S. Osindero, "Conditional generative adversarial nets," arXiv preprint arXiv:1411.1784. 2014.
  10. 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. https://doi.org/10.3745/KTSDE.2021.10.2.73
  11. Y. Jiang, Z. Lian, Y. Tang, and J. Xiao, "DCFont: An end-toend deep chinese font generation system," SIGGRAPH Asia 2017, Technical Briefs, 2017.
  12. 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.
  13. 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.
  14. 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.
  15. 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.
  16. D.P. Kingma and M. Welling, "Auto-encoding variational bayes," Proceedings of International Conference on Learning Representations, 2014.
  17. 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.