Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

MetaScript: Few-Shot Handwritten Chinese Content Generation via Generative Adversarial Networks (2312.16251v1)

Published 25 Dec 2023 in cs.CV and cs.AI

Abstract: In this work, we propose MetaScript, a novel Chinese content generation system designed to address the diminishing presence of personal handwriting styles in the digital representation of Chinese characters. Our approach harnesses the power of few-shot learning to generate Chinese characters that not only retain the individual's unique handwriting style but also maintain the efficiency of digital typing. Trained on a diverse dataset of handwritten styles, MetaScript is adept at producing high-quality stylistic imitations from minimal style references and standard fonts. Our work demonstrates a practical solution to the challenges of digital typography in preserving the personal touch in written communication, particularly in the context of Chinese script. Notably, our system has demonstrated superior performance in various evaluations, including recognition accuracy, inception score, and Frechet inception distance. At the same time, the training conditions of our model are easy to meet and facilitate generalization to real applications.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. Adversarial generation of handwritten text images conditioned on sequences. In 2019 international conference on document analysis and recognition (ICDAR), pages 481–486. IEEE, 2019.
  2. Realistic handwriting generation using recurrent neural networks and long short-term networks. In Proceedings of the Third International Conference on Computational Intelligence and Informatics: ICCII 2018, pages 651–661. Springer, 2020.
  3. Generating handwritten chinese characters using cyclegan. In 2018 IEEE winter conference on applications of computer vision (WACV), pages 199–207. IEEE, 2018a.
  4. Chinese handwriting imitation with hierarchical generative adversarial network. In BMVC, page 290, 2018b.
  5. Shi-Kuo Chang. An interactive system for chinese character generation and retrieval. IEEE Transactions on Systems, Man, and Cybernetics, SMC-3(3):257–265, 1973.
  6. Tgan: Deep tensor generative adversarial nets for large image generation. arXiv preprint arXiv:1901.09953, 2019.
  7. Generative multi-adversarial networks. arXiv preprint arXiv:1611.01673, 2016.
  8. Segan: Segmenting and generating the invisible. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 6144–6153, 2018.
  9. Scrabblegan: Semi-supervised varying length handwritten text generation, 2020.
  10. An oscillatory neuromotor model of handwriting generation. International journal of document analysis and recognition (ijdar), 10:69–84, 2007.
  11. Multi-agent diverse generative adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8513–8521, 2018.
  12. Alex Graves. Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850, 2013.
  13. Zero-shot generation of training data with denoising diffusion probabilistic model for handwritten chinese character recognition. arXiv preprint arXiv:2305.15660, 2023.
  14. A review on generative adversarial networks: Algorithms, theory, and applications, 2020.
  15. Diff-font: Diffusion model for robust one-shot font generation. arXiv preprint arXiv:2212.05895, 2022.
  16. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  17. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, 30, 2017.
  18. Automatic personality prediction based on users’ chinese handwriting change. In CCF Conference on Computer Supported Cooperative Work and Social Computing, pages 435–449. Springer, 2022.
  19. W-net: One-shot arbitrary-style chinese character generation with deep neural networks. In Neural Information Processing, pages 483–493, Cham, 2018. Springer International Publishing.
  20. Alexia Jolicoeur-Martineau. The relativistic discriminator: a key element missing from standard gan. arXiv preprint arXiv:1807.00734, 2018.
  21. What is the reward for handwriting? — a handwriting generation model based on imitation learning. In 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pages 109–114, 2020.
  22. A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4401–4410, 2019.
  23. Analyzing and improving the image quality of stylegan. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 8110–8119, 2020.
  24. Synthesizing and imitating handwriting using deep recurrent neural networks and mixture density networks. In 2018 9th International Conference on Computing, Communication and Networking Technologies (ICCCNT), pages 1–6, 2018.
  25. Photo-realistic single image super-resolution using a generative adversarial network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4681–4690, 2017.
  26. Faceshifter: Towards high fidelity and occlusion aware face swapping. arXiv preprint arXiv:1912.13457, 2019a.
  27. Improving gan-based calligraphy character generation using graph matching. In 2019 IEEE 19th International Conference on Software Quality, Reliability and Security Companion (QRS-C), pages 291–295. IEEE, 2019b.
  28. Calliffusion: Chinese calligraphy generation and style transfer with diffusion modeling. arXiv preprint arXiv:2305.19124, 2023.
  29. Casia online and offline chinese handwriting databases. In 2011 international conference on document analysis and recognition, pages 37–41. IEEE, 2011.
  30. Coupled generative adversarial networks. Advances in neural information processing systems, 29, 2016.
  31. Handwritten text generation via disentangled representations. IEEE Signal Processing Letters, 28:1838–1842, 2021.
  32. Attribute-guided face generation using conditional cyclegan. In Proceedings of the European conference on computer vision (ECCV), pages 282–297, 2018.
  33. Handwriting generation and synthesis: A review. In 2022 Second International Conference on Power, Control and Computing Technologies (ICPC2T), pages 1–6, 2022.
  34. Olof Mogren. C-rnn-gan: Continuous recurrent neural networks with adversarial training. arXiv preprint arXiv:1611.09904, 2016.
  35. Characterization and computation of local nash equilibria in continuous games. In 2013 51st Annual Allerton Conference on Communication, Control, and Computing (Allerton), pages 917–924. IEEE, 2013.
  36. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pages 234–241. Springer, 2015.
  37. Improved techniques for training gans. Advances in neural information processing systems, 29, 2016.
  38. Efficientnetv2: Smaller models and faster training. In International conference on machine learning, pages 10096–10106. PMLR, 2021.
  39. Generating videos with scene dynamics. Advances in neural information processing systems, 29, 2016.
  40. High-resolution image synthesis and semantic manipulation with conditional gans. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8798–8807, 2018a.
  41. Esrgan: Enhanced super-resolution generative adversarial networks. In Proceedings of the European conference on computer vision (ECCV) workshops, pages 0–0, 2018b.
  42. Automatic generation of personal chinese handwriting by capturing the characteristics of personal handwriting. In Twenty-First IAAI Conference, 2009.
  43. Seqgan: Sequence generative adversarial nets with policy gradient. In Proceedings of the AAAI conference on artificial intelligence, 2017.
  44. Unsupervised image super-resolution using cycle-in-cycle generative adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pages 701–710, 2018.
  45. Fully convolutional adaptation networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 6810–6818, 2018.
  46. Easy generation of personal chinese handwritten fonts. In 2011 IEEE international conference on multimedia and expo, pages 1–6. IEEE, 2011.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Xiangyuan Xue (4 papers)
  2. Kailing Wang (5 papers)
  3. Jiazi Bu (6 papers)
  4. Qirui Li (14 papers)
  5. Zhiyuan Zhang (129 papers)
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now