Owing to the complex structure of Chinese characters and the huge number of Chinese characters, it is very challenging and time consuming for artists to design a new font of Chinese characters. Therefore, the generation of Chinese characters and the transformation of font styles have become research hotspots. At present, most of the models on Chinese character transformation cannot generate multiple fonts, and they are not doing well in faking fonts. In this article, the authors propose a novel method of Chinese character fonts transformation and generation based on generative adversarial networks. The authors’ model is able to generate multiple fonts at once through font style-specifying mechanism and it can generate a new font at the same time if the authors combine the characteristics of existing fonts.

References

1. 1)
  - 12. Zhu, J.-Y., Park, T., Isola, P., et al: ‘Unpaired image-to-image translation using cycle-consistent adversarial networks’. IEEE Int. Conf. on Computer Vision, ICCV 2017, Venice, Italy, 22–29 October 2017, pp. 2242–2251.
2. 2)
  - 1. Xu, S., Jiang, H., Jin, T., et al: ‘Automatic generation of Chinese calligraphic writings with style imitation’, IEEE Intell. Syst., 2009, 24, (2), pp. 44–53, DOI: 10.1109/MIS.2009.23.
3. 3)
  - 19. Tzeng, E., Hoffman, J., Saenko, K., et al: ‘Adversarial discriminative domain adaptation’. 2017 IEEE Conf. on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21–26 July 2017, pp. 2962–2971.
4. 4)
  - 9. Sun, D., Ren, T., Li, C., et al: ‘Learning to write stylized Chinese characters by reading a handful of examples’. Proc. of the Twenty-Seventh Int. Joint Conf. on Artificial Intelligence, IJCAI 2018, Stockholm, Sweden, 13–19 July 2018, pp. 920–927.
5. 5)
  - 16. Lin, K.-Y., Wang, G.: ‘Hallucinated-iqa: no-reference image quality assessment via adversarial learning’. IEEE Conf. on Computer Vision and Pattern Recognition, Salt Lake City, 2018, pp. 732–741.
6. 6)
  - 4. Zhang, X.-Y., Yin, F., Zhang, Y.-M., et al: ‘Drawing and recognizing Chinese characters with recurrent neural network’, IEEE Trans. Pattern Anal. Mach. Intell., 2018, 40, (4), pp. 849–862.
7. 7)
  - 13. Kim, T., Cha, M., Kim, H., et al: ‘Learning to discover cross-domain relations with generative adversarial networks’. Proc. of the 34th Int. Conf. on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6–11 August 2017, pp. 1857–1865.
8. 8)
  - 7. Gulrajani, I., Ahmed, F., Arjovsky, M., et al: ‘Improved training of Wasserstein GANs’. Advances in Neural Information Processing Systems 30: Annual Conf. on Neural Information Processing Systems 2017, Long Beach, CA, USA, 4–9 December 2017, pp. 5769–5779.
9. 9)
  - 8. Tian, Y.: ‘Zi2zi: master Chinese calligraphy with conditional adversarial networks’, 2017.
10. 10)
  - 3. Zhou, B., Wang, W., Chen, Z.: ‘Easy generation of personal Chinese handwritten fonts’. Proc. of the 2011 IEEE Int. Conf. on Multimedia and Expo, ICME 2011, Barcelona, Catalonia, Spain, 11–15 July 2011, pp. 1–6.
11. 11)
  - 11. Jiang, H., Yang, G., Huang, K., et al: ‘W-net: one-shot arbitrary-style Chinese character generation with deep neural networks’. Neural Information Processing – 25th Int. Conf., ICONIP 2018, Siem Reap, Cambodia, Proceedings, Part V, 13–16 December 2018, pp. 483–493.
12. 12)
  - 22. Nguyen, H.V., Bai, L.: ‘Cosine similarity metric learning for face verification’. Asian Conf. on Computer Vision, Queenstown, New Zealand, 2010, https://ieeexplore.ieee.org/document/8573146.
13. 13)
  - 15. Yang, E., Liu, T., Deng, C., et al: ‘Adversarial examples for hamming space search’, IEEE Trans. Cybern., 2018, pp. 1–12.
14. 14)
  - 5. Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., et al: ‘Generative adversarial networks’, CoRR, vol. abs/1406.2661, 2014.
15. 15)
  - 14. Choi, Y., Choi, M.-J., Kim, M., et al: ‘Stargan: unified generative adversarial networks for multi-domain image-to-image translation’. 2018 IEEE Conf. on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, 2018, pp. 8789–8797.
16. 16)
  - 21. Sheikh, H.R., Wang, Z., Bovik, A.C.: ‘Image quality assessment: from error visibility to structural similarity’, IEEE Trans. Image Process., 2004, 13, (4), pp. 600–612, DOI: 10.1007/978-3-642-19309-5_55.
17. 17)
  - 2. Xu, S., Jin, T., Jiang, H., et al: ‘Automatic generation of personal Chinese handwriting by capturing the characteristics of personal handwriting’. Proc. of the Twenty-First Conf. on Innovative Applications of Artificial Intelligence, Pasadena, California, USA, 14–16 July 2009.
18. 18)
  - 17. Ren, H., Chen, D., Wang, Y.: ‘RAN4IQA: restorative adversarial nets for no-reference image quality assessment’. AAAI Conf. on Artificial Intelligence, New Orleans, Louisiana, USA, 2018, pp. 7308–7314.
19. 19)
  - 18. Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., et al: ‘Generative adversarial nets’. Advances in Neural Information Processing Systems 27, Montreal, Quebec, Canada, 8–13 December 2014, pp. 2672–2680.
20. 20)
  - 6. Brock, A., Donahue, J., Simonyan, K.: ‘Large scale GAN training for high fidelity natural image synthesis’, CoRR, vol. abs/1809.11096, 2018.
21. 21)
  - 20. He, K., Zhang, X., Ren, S., et al: ‘Deep residual learning for image recognition’. 2016 IEEE Conf. on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27–30 June 2016, pp. 770–778.
22. 22)
  - 10. Chang, J., Gu, Y., Zhang, Y.: ‘Chinese typography transfer’, CoRR, vol. abs/1707.04904, 2017, Withdrawn.

Learning one-to-many stylised Chinese character transformation and generation by generative adversarial networks

References

Related content