journal article·2025-02-25Open access

A novel unsupervised contrastive learning framework for ancient Yi script character dataset construction

Xiaojun Bi, Ziwei Sun, Zheng Chen

npj Heritage Science· Volume 13· Issue 1

Abstract

The ancient Yi books have a long history and are one of the most important cultural heritages of humanity. Currently, Yi character image recognition datasets are all constructed by manual handwriting. Nevertheless, there are significant feature differences between handwritten character images and real ancient manuscript character images. This limits their effectiveness in practical ancient manuscript character recognition scenarios. To address these issues, we propose a novel dataset construction method to construct a real-world character dataset Yi_1047. Our method first uses an unsupervised contrastive learning model to perform accurate feature extraction. It applies this to a large number of unlabeled single-character images from real ancient manuscripts. Then, we use image retrieval and clustering methods to construct a real Yi script single-character dataset. It contains 1047 classes of ancient Yi script characters, totaling 265,094 character images. It is currently the only non-manually handwritten ancient Yi single-character dataset. Additionally, for highly similar characters, we specifically construct a comprehensive list of similar characters. Extensive experimental results demonstrate the effectiveness and superiority of our proposed method for constructing the Yi_1047 dataset. This innovative method not only achieves the digital preservation of ancient Yi script, but our experiments also show that it plays a role in constructing single-character recognition datasets for other ancient books.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Natural Language Processing Techniques · Handwritten Text Recognition Techniques · Topic Modeling

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (38)

Show source-provided references
1. Gu, W. Reconstructing Yi history. in Perspectives on the Yi of Southwest China Vol. 26, 21 (University of California Press, 2001).10.1525/california/9780520219885.003.0002 ↗
2. Bao, H. & Bao, A. The current situation of collection and research on ancient books of Chinese ethnic minorities. Inn Mongolia Soc Sci 6, 9–14 (2004).
3. Jinwei, M. To Study the Origin and Development of the Written Language of Yi People. Ph.D. thesis, Southwest University (2010).
4. Zhang, F. et al. Pay attention to the preservation status of ancient Yi books in China. China’s Ethnic Groups. 10, 65 (2005).
5. Lu, Y.-p, Wu, X. & Huang, W.-h. The digital construction of documents in Yi language ancient books of northwestern Guizhou. J. Guizhou Univ. Eng. Sci. 28, 18–22 (2010).
6. Luo, Y., Sun, Y. & Bi, X. Multiple attentional aggregation network for handwritten dongba character recognition. Expert Syst. Appl. 213, 118865 (2023).10.1016/j.eswa.2022.118865 ↗
7. Zhao, H., Chu, H., Zhang, Y. & Jia, Y. Improvement of ancient shui character recognition model based on convolutional neural network. IEEE Access 8, 33080–33087 (2020).10.1109/ACCESS.2020.2972807 ↗
8. Chen, S., Han, X., Wang, X. & Ma, H. A recognition method of ancient Yi script based on deep learning. Int. J. Comput. Inf. Eng. 13, 504–511 (2019).
9. Liu, X. et al. One shot ancient character recognition with Siamese similarity network. Sci. Rep. 12, 14820 (2022).10.1038/s41598-022-18986-z ↗
10. Chen, S., Yang, Y., Liu, X. & Zhu, S. Dual discriminator gan: Restoring ancient Yi characters. Trans. Asian Low. Resour. Lang. Inf. Process. 21, 1–23 (2022).10.1145/3543851 ↗
11. Xiaodong, J., Wendong, G. & Jie, Y. Handwritten Yi character recognition with density-based clustering algorithm and convolutional neural network. In 2017 IEEE International Conference on Computational Science and Engineering (CSE) and IEEE International Conference on Embedded and Ubiquitous Computing (EUC) Vol. 1, 337–341 (IEEE, 2017).10.1109/CSE-EUC.2017.67 ↗
12. LeCun, Y., Bottou, L., Bengio, Y. & Hafner, P. Gradient-based learning applied to document recognition. In Proceedings of the IEEE, vol. 86, pp. 2278–2324 (IEEE, 1998).10.1109/5.726791 ↗
13. Liu, C.-L., Yin, F., Wang, D.-H. & Wang, Q.-F. Casia online and offline Chinese handwriting databases. In 2011 International Conference on Document Analysis and Recognition 37–41 (IEEE, 2011).10.1109/ICDAR.2011.17 ↗
14. He, K., Fan, H., Wu, Y., Xie, S. & Girshick, R. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition 9729–9738 (IEEE, 2020).10.1109/CVPR42600.2020.00975 ↗
15. Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. A simple framework for contrastive learning of visual representations. In International Conference on Machine Learning 1597–1607 (PMLR, 2020).
16. Grill, J.-B. et al. Bootstrap your own latent—a new approach to self-supervised learning. Adv. Neural Inf. Process. Syst. 33, 21271–21284 (2020).
17. Caron, M. et al. Unsupervised learning of visual features by contrasting cluster assignments. Adv. Neural Inf. Process. Syst. 33, 9912–9924 (2020).
18. Li, Y. et al. Contrastive clustering. In Proceedings of the AAAI conference on artificial intelligence Vol. 35, 8547–8555 (AAAI Press, 2021).10.1609/aaai.v35i10.17037 ↗
19. Oquab, M. et al. DINOv2: Learning Robust Visual Features without Supervision. In Transactions on Machine Learning Research 2835–8856 (TMLR, 2024).
20. Caron, M. et al. Emerging properties in self-supervised vision transformers. In Proceedings of the IEEE/CVF International Conference on Computer Vision 9650–9660 (IEEE, 2021).10.1109/ICCV48922.2021.00951 ↗
21. Russakovsky, O. et al. Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211–252 (2015).10.1007/s11263-015-0816-y ↗
22. Krizhevsky, A. & Hinton, G. Learning multiple layers of features from tiny images. https://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf (University of Toronto, 2009).
23. Van Gansbeke, W., Vandenhende, S., Georgoulis, S., Proesmans, M. & Van Gool, L. Scan: learning to classify images without labels. In European Conference on Computer Vision 268–285 (Springer, 2020).10.1007/978-3-030-58607-2_16 ↗
24. Amrani, E., Karlinsky, L. & Bronstein, A. Self-supervised classification network. In European Conference on Computer Vision 116–132 (Springer, 2022).10.1007/978-3-031-19821-2_7 ↗
25. Wang, J. Qu, S. Southwest Yi zhi (Guizhou Ethnic Publishing House, 2015).
26. Li, J. Zhou, P. Xiong, C. Hoi, S. Prototypical contrastive learning of unsupervised representations. in Proc. 9th Int. Conf. Learn. Representations, Austria, May (2021).
27. Radford, A., Metz, L. & Chintala, S. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015).
28. Donahue, J. & Simonyan, K. Large scale adversarial representation learning. Advances in neural information processing systems 32 (2019).
29. He, K. et al. Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 16000–16009 (IEEE, 2022).10.1109/CVPR52688.2022.01553 ↗
30. Krizhevsky, A., Sutskever, I. & Hinton, G. E. Imagenet classification with deep convolutional neural networks. Commun. ACM 60, 84–90 (2017).10.1145/3065386 ↗
31. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A. & Chen, L.-C. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 4510–4520 (IEEE, 2018).10.1109/CVPR.2018.00474 ↗
32. Iandola, F. N. et al. Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <0.5 mb model size. arXiv preprint arXiv:1602.07360 (2016).
33. Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. In: Proceedings of the 3rd International Conference on Learning Representations. San Diego, CA, USA, (2015).
34. Tan, M. & Le, Q. Efficientnet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning 6105–6114 (PMLR, 2019).
35. He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 770–778 (IEEE, 2016).10.1109/CVPR.2016.90 ↗
36. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J. & Wojna, Z. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2818–2826 (IEEE, 2016).10.1109/CVPR.2016.308 ↗
37. Ma, N., Zhang, X., Zheng, H.-T. & Sun, J. Shufflenet v2: practical guidelines for efficient CNN architecture design. In Proceedings of the European Conference on Computer Vision (ECCV) 116–131 (Springer, 2018).10.1007/978-3-030-01264-9_8 ↗
38. Chen, X., Fan, H., Girshick, R. & He, K. Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020).