Abstract
Synthesizing Chinese characters with consistent style using few stylized examples is challenging. Existing models struggle to generate arbitrary style characters with limited examples. In this paper, we propose the Generalized W-Net, a novel class of W-shaped architectures that addresses this. By incorporating Adaptive Instance Normalization and introducing multi-content, our approach can synthesize Chinese characters in any desired style, even with limited examples. It handles seen and unseen styles during training and can generate new character contents. Experimental results demonstrate the effectiveness of our approach.
K. Huang—This research is funded by XJTLU Research Development Funding 20-02-60. Computational resources utilized in this research are provided by the School of Robotics, XJTLU Entrepreneur College (Taicang), and the School of Advanced Technology, Xi’an Jiaotong-Liverpool University.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
The input of the W-Net architecture in [9] represents a special case, involving only one single content prototype with a standard font. In most cases, the styles are pre-selected and fixed prior to training or utilization.
- 2.
In the proposed Generalized W-Net and W-Net architecture [9], N can be changed during testing.
- 3.
The generated character will be noted as \(G(x^{c_m}_j,x^i_{s_n})\) for simplicity.
- 4.
The output of the style reference encoder \(Enc_r(x^h_{p_1},x^h_{p_2},...,x^h_{p_L})\) is connected to the Dec using shortcut or residual/dense block connections (see Sect. 3.2).
- 5.
The specific normalization method may vary across implementations (see Sect. 3.3).
- 6.
The encoded outputs will be referred to as \(Enc_p(x^{c_m}_j)\) and \(Enc_r(x^i_{s_n})\).
References
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of wasserstein gans. In: Advances in Neural Information Processing Systems, pp. 5767–5777 (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630–645. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_38
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1501–1510 (2017)
Huang, X., Liu, M.Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 172–189 (2018)
Jiang, H., Huang, K., Zhang, R.: Field support vector regression. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, E.S. (eds.) Neural Information Processing. ICONIP 2017. LNCS, vol. 10634, pp. 699–708. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-70087-8_72
Jiang, H., Huang, K., Zhang, R., Hussain, A.: Style neutralization generative adversarial classifier. In: Ren, J., et al. (eds.) BICS 2018. LNCS (LNAI), vol. 10989, pp. 3–13. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00563-4_1
Jiang, H., Yang, G., Huang, K., Zhang, R.: W-Net: one-shot arbitrary-style Chinese character generation with deep neural networks. In: Cheng, L., Leung, A.C.S., Ozawa, S. (eds.) ICONIP 2018. LNCS, vol. 11305, pp. 483–493. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-04221-9_43
Liu, C.L., Yin, F., Wang, D.H., Wang, Q.F.: CASIA online and offline Chinese handwriting databases. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 37–41, September 2011. https://doi.org/10.1109/ICDAR.2011.17
Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier GANs. arXiv preprint arXiv:1610.09585 (2016)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)
Shieh, J.C.: The unified phonetic transcription for teaching and learning Chinese languages. Turk. Online J. Educ. Technol.-TOJET 10(4), 355–369 (2011)
Taigman, Y., Polyak, A., Wolf, L.: Unsupervised cross-domain image generation. arXiv preprint arXiv:1611.02200 (2016)
Yang, X., Huang, K., Zhang, R., Hussain, A.: Learning latent features with infinite nonnegative binary matrix trifactorization. IEEE Trans. Emerg. Top. Comput. Intell. 99, 1–14 (2018)
Zhang, Y., Zhang, Y., Cai, W.: Separating style and content for generalized style transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8447–8455 (2018)
Zhang, Y., Zhang, Y., Cai, W.: A unified framework for generalizable style transfer: style and content separation. arXiv preprint arXiv:1806.05173 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Jiang, H., Yang, G., Cheng, F., Huang, K. (2024). Generalized W-Net: Arbitrary-Style Chinese Character Synthesization. In: Ren, J., et al. Advances in Brain Inspired Cognitive Systems. BICS 2023. Lecture Notes in Computer Science(), vol 14374. Springer, Singapore. https://doi.org/10.1007/978-981-97-1417-9_18
Download citation
DOI: https://doi.org/10.1007/978-981-97-1417-9_18
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-1416-2
Online ISBN: 978-981-97-1417-9
eBook Packages: Computer ScienceComputer Science (R0)