Abstract
Glyph perturbation is an increasing subject in information embedding. It can be generated by moving strokes of Chinese characters to convey secret messages. However, the generation is limited by the large number and diverse fonts of Chinese characters. Several attempts have been made to generate Chinese characters in the font transfer based on deep learning, up to now no studies have investigated font transfer for glyph perturbation. We propose a font transfer method for glyph perturbation of Chinese characters named Glyph-Font, which focuses on the position of strokes while transferring fonts. More specifically, we first build an image dataset for glyph perturbation of Chinese characters through perturbing strokes. Secondly, the generator based on a parallel auto-encoder simultaneously generates four glyph perturbations for each character in target fonts. In addition, a discriminator is designed to optimize the network by calculating the difference between real and generated images of Chinese characters. Finally, perturbation loss and patch-pixel loss are defined to amend incorrectly generated pixels and distinguish position changes of strokes. Experimental results demonstrate that our proposed Glyph-Font has the potential to generate glyph perturbations of Chinese characters automatically in various fonts.
Supported by National Natural Science Foundation of China (62071267).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Lian, Z., Zhao, B., Xiao, J.: Automatic generation of large-scale handwriting fonts via style learning. In SIGGRAPH ASIA 2016 Technical Briefs, pp. 1–4. Association for Computing Machinery, New York (2016) https://doi.org/10.1145/3005358.3005371
Lian, Z., Zhao, B., Chen, X., Xiao, J.: EasyFont: a style learning-based system to easily build your large-scale handwriting fonts. ACM Trans. Graph. 38(1), 1–18 (2018). https://doi.org/10.1145/3213767
Zhang, X.-Y., Yin, F., Zhang, Y.-M., Liu, C.-L., Bengio, Y.: Drawing and recognizing Chinese characters with recurrent neural network. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 849–862 (2018). https://doi.org/10.1109/TPAMI.2017.2695539
Wen, C., et al.: Handwritten Chinese font generation with collaborative stroke refinement. arXiv preprint arXiv: 1904.13268 (2019)
Lin, X., Li, J., Zeng, H., Ji, R.: Font generation based on least squares conditional generative adversarial nets. Multimedia Tools Appl. 78(1), 783–797 (2018). https://doi.org/10.1007/s11042-017-5457-4
Huang, Y., He, M., Jin, L., Wang, Y.: RD-GAN: few/zero-shot Chinese character style transfer via radical decomposition and rendering. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 156–172. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58539-6_10
Sun, D., Ren, T., Li, C., Su, H., Zhu, J.: Learning to write stylized Chinese characters by reading a handful of examples. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence, pp. 920–927. International Joint Conferences on Artificial Intelligence Organization, Stockholm (2018). https://doi.org/10.24963/ijcai.2018/128
Zhang, Y., Zhang, Y., Cai, W.: Separating style and content for generalized style transfer. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8447–8455. IEEE, Salt Lake City (2018). https://doi.org/10.1109/CVPR.2018.00881
Zhang, Y., Zhang, Y., Cai, W.: A unified framework for generalizable style transfer: style and content separation. IEEE Tran. Image Process. 29, 4085–4098 (2020). https://doi.org/10.1109/TIP.2020.2969081
Goodfellow, I.J., et al.: Generative adversarial nets. In: Proceedings of the 27th International Conference on Neural Information Processing Systems, pp. 2672–2680. MIT Press, Cambridge (2014)
Sun, D., Zhang, Q., Yang, J.: Pyramid embedded generative adversarial network for automated font generation. In: 24th International Conference on Pattern Recognition, pp. 976–981. IEEE, Beijing (2018) https://doi.org/10.1109/ICPR.2018.8545701
Isola, P., Zhu, J.-Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 5967–5976. IEEE, Honolulu (2017) https://doi.org/10.1109/CVPR.2017.632
Ren, C., Lyu, S., Zhan, H., Lu, Y.: SAFont: automatic font synthesis using self-attention mechanisms. Aust. J. Intell. Inf. Process. Syst. 16(2), 19–25 (2019)
Chang, J., Gu, Y., Zhang, Y.: Chinese typeface transformation with hierarchical generative adversarial network. arXiv preprint arXiv: 1711.06448 (2017)
Chang, J., Gu, Y., Zhang, Y, Wang, Y.: Chinese handwriting imitation with hierarchical generative adversarial network. In: British Machine Vision Conference, pp. 1–12. BMVA Press, Newcastle (2018)
Chang, B., Zhang, Q., Pan, S., Meng, L.: Generating handwritten Chinese characters using CycleGAN. In: Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision, pp. 199–207. IEEE, Lake Tahoe (2018) https://doi.org/10.1109/WACV.2018.00028
Zhang, Y.: Generating handwritten Chinese character with GANs. East China Normal University, Shanghai (2019). (
(2019))Zeng, J., Chen, Q., Liu, Y., Wang, M., Yao, Y.: StrokeGAN: reducing mode collapse in Chinese font generation via stroke encoding. arXiv preprint arXiv: 2012.08687 (2020)
Tian, Y.: Zi2Zi. https://github.com/kaonashi-tyc/zi2zi/, Accessed 9 Aug 2019
Chen, J., Xu, X., Ji, Y., Chen, H.: Learning to create multi-stylized Chinese character fonts by generative adversarial networks. In: ACM TURC ’19 Proceedings of the ACM Turing Celebration Conference, pp. 1–6. Association for Computing Machinery, Chengdu (2019) https://doi.org/10.1145/3321408.3322631
Chen, J., Chen, H., Xu, X., Ji, Y., Chen, L.: Learning to write multi-stylized Chinese characters by generative adversarial networks. J. Univ. Electron. Sci. Technol. China 48(5), 674–678 (2019). (
48(5), 674–678 (2019)) https://doi.org/10.3969/j.issn.1001-0548.2019.05.003Wu, S.-J., Yang, C.-Y., Hsu, J.-Y.: CalliGAN: style and structure-aware Chinese calligraphy character generator. arXiv preprint arXiv: 2005.12500 (2020)
Lyu, P., Bai, X., Yao, C., Zhu, Z., Huang, T., Liu, W.: Auto-encoder guided GAN for Chinese calligraphy synthesis. In: Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition, pp. 1095–1100. IEEE Computer Society, Kyoto (2017) https://doi.org/10.1109/ICDAR.2017.181
Jiang, Y., Lian, Z., Tang, Y., Xiao, J.: DCFont: an end-to-end deep Chinese font generation system. In: SIGGRAPH Asia 2017 Technical Briefs, pp. 1–4. Association for Computing Machinery, New York (2017) https://doi.org/10.1145/3145749.3149440
Liu, X., Meng, G., Chang, J., Hu, R., Xiang, S., Pan, C.: Decoupled representation learning for Character glyph synthesis. IEEE Trans. Multimedia., 1 (2021). https://doi.org/10.1109/TMM.2021.3072449
Yang, S., Liu, J., Wang, W., Guo, Z.: TET-GAN: text effects transfer via stylization and de-stylization. In: Proceedings of the 32nd AAAI Conference on Artificial Intelligence, pp. 1238–1245. AAAI Press, Hilton Hawaiian Village (2019) :https://doi.org/10.1609/aaai.v33i01.33011238
Gao, Y., Guo, Y., Lian, Z., Tang, Y., Xiao, J.: Artistic glyph image synthesis via one-stage few-shot learning. ACM Trans. Graph. 38(6), 1–12 (2019). https://doi.org/10.1145/3355089.3356574
Xiao, C., Zhang, C., Zheng, C.: FontCode: embedding information in text documents using glyph perturbation. ACM Trans. Graph. 37(2), 1–16 (2018). https://doi.org/10.1145/3152823
Chang, B., Zhang, Q.: Rewrite2: a GAN based Chinese font transfer algorithm. https://github.com/changebo/Rewrite2/, Accessed 18 Mar 2017
Perarnau, G., van de Weijer, J., Raducanu, B., Álvarez, J. M.: Invertible conditional gans for image editing. arXiv preprint arXiv: 1611.06355 (2016)
Chang, J., Gu, Y.: Chinese typography transfer. arXiv preprint arXiv: 1707.04904v1 (2017)
Wang, T., Liu, Y., Zheng, X., Dai, H.-N., Jia, W., Xie, M.: Edge-based communication optimization for distributed federated learning. IEEE Trans. Netw. Sci. Eng., 1 (2021) https://doi.org/10.1109/TNSE.2021.3083263
Wang, T., Lu, Y., Wang, J., Dai, H.-N., Zheng, X., Jia, W.: EIHDP: edge-intelligent hierarchical dynamic pricing based on cloud-edge-client collaboration for IoT systems. IEEE Trans. Comput. 70(8), 1285–1298 (2021). https://doi.org/10.1109/TC.2021.3060484
Wang, T., Bhuiyan, M.Z.A., Wang, G., Qi, L., Wu, J., Hayajneh, T.: Preserving balance between privacy and data integrity in edge-assisted internet of things. IEEE Internet Things J. 7(4), 2679–2689 (2020). https://doi.org/10.1109/JIOT.2019.2951687
(2019))
48(5), 674–678 (2019)) Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, C., Zhu, Y., Shen, Z., Wang, D., Wu, G., Yao, Y. (2022). Font Transfer Based on Parallel Auto-encoder for Glyph Perturbation via Strokes Moving. In: Lai, Y., Wang, T., Jiang, M., Xu, G., Liang, W., Castiglione, A. (eds) Algorithms and Architectures for Parallel Processing. ICA3PP 2021. Lecture Notes in Computer Science(), vol 13156. Springer, Cham. https://doi.org/10.1007/978-3-030-95388-1_39
Download citation
DOI: https://doi.org/10.1007/978-3-030-95388-1_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-95387-4
Online ISBN: 978-3-030-95388-1
eBook Packages: Computer ScienceComputer Science (R0)