Restoration of oracle bone inscriptions using a fast residual shrinkage denoising network with fractal gradient
Source abstract
Abstract
To address the low-texture and strong-edge characteristics of oracle bone inscription images, this research proposes a restoration method based on a fast residual shrinkage denoising network integrated with adaptive box-counting fractal gradient features. The adaptive differential box counting fractal gradient, when employed as a loss function, can be dynamically adjusted according to the local characteristics of the image, thereby enabling more accurate gradient estimation and enhanced representation of strong edge features. By integrating sampling pairs and soft thresholding mechanisms into the residual denoising network, the model achieves improved denoising performance while preserving edge details, thus accomplishing image restoration tasks more effectively. Compared with traditional approaches, the method achieves superior performance in both subjective visual quality and objective evaluation metrics, substantially improving edge clarity in oracle bone inscriptions.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Image and Signal Denoising Methods · Generative Adversarial Networks and Image Synthesis · Advanced Computing and Algorithms
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (34)
Show source-provided references
1. Liu, J. et al. OBI-CMF: Self-supervised learning with contrastive masked frequency modeling for oracle bone inscription recognition. Herit. Sci. 13, 55 (2025).10.1038/s40494-025-01644-8 ↗
2. Wu, R. et al. A text image dual conditional stable diffusion model for oracle bone inscription decipherment. Herit. Sci. 13, 453 (2025).10.1038/s40494-025-02019-9 ↗
3. Gu, S. T. Review on digitization processing of jiaguwen. J. Xihua Univ. (Nat. Sci. Ed.) 29, 38–42 (2010).
4. Huang, T. S. On academic value and research methods of restoration of oracle bone inscription fragments. Palace Mus. J. 54, 7–13 (2011).
5. Wang, A. M. et al. Research on com⁃ putermatching of inscriptions on tortoise fragments. Comput. Eng. Des. 32, 3570–3573 (2011).
6. Gu, S. T. Inpainting method of oracle-bone inscriptions based on iterated function system and fractal interpolation. Sci. Technol. Eng. 18, 87–92 (2018).
7. Tian, Y. et al. The research on rejoining of the oracle bone rubbings based on curve matching. Trans. Asian Low.-Resour. Lang. Inf. Process. 20, 1–17 (2021).
8. Zhang, C. et al. Data-Driven Oracle Bone Rejoining: a dataset and practical self-supervised learning scheme. In Proc. 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery (ACM). 4482–4492 (2022).10.1145/3534678.3539050 ↗
9. Zhang, Z., Guo, A. & Li, B. Internal similarity network for rejoining oracle bone fragment images. Symmetry 14, 1464–1481 (2022).10.3390/sym14071464 ↗
10. Wang, S. B. et al. Coarse-to-fine generative model for oracle bone inscriptions inpainting. In Proc. 1st Workshop on Machine Learning for Ancient Languages, Association for Computational Linguistics (ACL). 107–114 (2024).10.18653/v1/2024.ml4al-1.12 ↗
11. Song, C. M., Qiao, M. Z. & Hong, Y. Edge gradient covariance guided restoration for oracle bone characters. J. Liaoning Univ. 46, 194–207 (2023).
12. Yue, Z. S. et al. Deep variational network toward blind image restoration. IEEE Trans. Pattern Anal. Mach. Intell. 46, 7011–7026 (2024).10.1109/TPAMI.2024.3365745 ↗
13. Zhang, K., Li, Y., Zuo, W. et al. Plug-and-play image restoration with deep denoiser prior. IEEE Trans. Pattern Anal. Mach. Intell. 44, 6360–6376 (2021).10.1109/TPAMI.2021.3088914 ↗
14. Zhang, K., Zuo, W. & Chen, Y. Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans. Image Process. 26, 3142–3155 (2017).10.1109/TIP.2017.2662206 ↗
15. Singh, P. & Shankar, A. A novel optical image denoising technique using convolutional neural network and anisotropic diffusion for real-time surveillance applications. J. Real.-Time Image Process. 5, 11554 (2021).
16. K. Zhang, W. M. Zuo, S. H. Gu, and L. Zhang. Learning deep CNN denosier prior for image restoration[C]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2808–2817 (IEEE, 2017).10.1109/CVPR.2017.300 ↗
17. Zhang, J., Zhao, D. B. & Gao, W. Group-based sparse representation for image restoration. IEEE Trans. Image Process. 23, 3336–3351 (2014).10.1109/TIP.2014.2323127 ↗
18. Zhang, J., Zhao, D. B. & Xiong, R. Q. Image restoration using joint statistical modeling in a space-transform domain. IEEE Trans. Circuits Syst. Video Technol. 24, 915–928 (2014).10.1109/TCSVT.2014.2302380 ↗
19. Xie, Y., Gu, S., Liu, Y. & Zhang, L. Weighted Schatten p-norm minimisation for image denoising and background subtraction. IEEE Trans. Image Process. 25, 4842–4857 (2016).10.1109/TIP.2016.2599290 ↗
20. Diwakar, M. & Singh, P. CT image denoising using multivariate model and its method noise thresholding in non-subsampled shearlet domain. Biomed. Signal Process. Control 57, 101754 (2020).10.1016/j.bspc.2019.101754 ↗
21. Diwakar, M., Singh, P. & Garg, D. Edge-guided filtering based CT image denoising using fractional order total variation. Biomed. signal Process. control 92, 106072 (2024).10.1016/j.bspc.2024.106072 ↗
22. Katta, S., Singh, P., Garg, D., Ravi, V. & Diwakar, M. A dual CT image denoising approach using guided filter and method-based noise in the NSST Domain. Open Bioinforma. J. 18, 25 (2024).
23. Egiazarian, K. & Katkovnik, V. Single image super-resolution via BM3D sparse coding. In Proc. European Signal Processing Conference, European Association for Signal Processing (EURASIP). 2849–2853 (2015).10.1109/EUSIPCO.2015.7362905 ↗
24. Ma, J., Peng, C. & Tian, X. Dbdnet: A deep boosting strategy for image denoising. IEEE Trans. Multimed. 24, 3157–3168 (2021).10.1109/TMM.2021.3094058 ↗
25. Canny, J. A computitional approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 8, 679–698 (1986).10.1109/TPAMI.1986.4767851 ↗
26. Rosenfeld, A. Computer vision: a source of models for biological visual process. IEEE Trans. Biomed. Eng. 36, 83–94 (1989).10.1109/10.16452 ↗
27. Zhao, Y. Z., Wang, Y. F. et al. Defect detection method for aerospace electronic assembly solder joints based on improved Canny algorithm. Comput. Meas. Control 36, 1–13 (2025).
28. Zhang, Y., Wang, P., Bao, F., Yao, X. & Lin, H. Single-image super-resolution based on rational fractal interpolation. IEEE Trans. Multimed. 22, 1407–1422 (2020).10.1109/TMM.2019.2943750 ↗
29. Li, Z., Chen, A. M. & Miao, T. J. A blind image inpainting model integrated with rational fractal interpolation information. Fractals 31, 1–14 (2023).10.1142/S0218348X23501293 ↗
30. Liu, Y. F., Zhang, Y. F. & Guo, Q. Image interpolation based on weighted and blended rational function. In Lecture Notes in Computer Science. 78–88 (Springer, Heidelberg, 2015).10.1007/978-3-319-16631-5_6 ↗
31. He, K., Zhang, X. & Ren. S. 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 ↗
32. Tai, Y., Yang, J. & Liu, X. Image super-resolution via deep recursive residual network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2790–2798 (IEEE, 2017).10.1109/CVPR.2017.298 ↗
33. Zhao, M. et al. Deep residual shrinkage networks for fault diagnosis. IEEE Trans. Ind. Inform. 16, 4681–4690 (2019).10.1109/TII.2019.2943898 ↗
34. Chen, T. Z. The OBC306 Dataset from “Yin Qi Wen Yuan”. Chinese Character Culture, 93–96 (2024).