Deep rejoining model and dataset of oracle bone fragment images
Source abstract
Abstract
Broken oracle bones record valuable information about ancient Chinese cultural heritage in the Shang Dynasty. However, many complete oracle bones have broken into pieces over the years, resulting in disjoining fragments scattered around the world, researchers have turned their attention to current technology to piece together oracle bone fragment images. A survey on rejoining object fragment algorithms and experiment datasets has been conducted, and it shows that the restoration work poses a serious challenge for current restoration models. To enhance the effectiveness of a deep rejoining model (DRM) with two stages, in the first stage, the longest similar edge segment (LSES) is proposed to match edge segments of two images, and a complete image rejoining (CIR) algorithm is given to rejoin the two images to be a complete image, in the second stage, we have embedded machine learning or deep learning methods into the DRM to determine whether the two images’ textures are continuity. In addition, a data set of oracle bone fragment image (OBFI) is given to evaluate current methods, it consists of three parts, and they are single high-resolution oracle bone fragment images, oracle bone fragment image pairs that can be rejoined together, and images that have rejoinable or unrejoinable textures. Extensive experiments on DRM and OBFI datasets demonstrate that DRM over previous state-of-the-art methods and the dataset can be used to evaluate the performance fragment rejoining algorithms.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Image Processing and 3D Reconstruction · Archaeological Research and Protection · Handwritten Text Recognition Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (34)
Show source-provided references
1. Chou, H.-H. & G.Opstad, D. Computer matching of oracle bone fragments: a preliminary report on a new research mehtod. Archaeology 26, 176–181 (1973).
2. Liu, Y.-G., Wang, T.-L. & Wang, J.-P. The application of the technique of 2d fragments stitching based on outline feature in rejoining oracle bones. In Proc. International Conference on Multimedia Information Networking and Security 964–968 (2010).10.1109/MINES.2010.208 ↗
3. Wang, A.-M., Liu, G.-Y., Ge, W.-Y., Zhou, H.-Y. & Wang, D.-L. Oracle computer-aided conjugation system design. Computer Eng. Appl. 46, 59–62 (2010).
4. Zhang, Z., Guo, A. & Li, B. Internal similarity network for rejoining oracle bone fragment images. Symmetry Basel 14, 1464 (2022).10.3390/sym14071464 ↗
5. Zhang, Z., Wang, Y.-T., Li, B., Guo, A. & Liu, C.-L. Deep rejoining model for oracle bone fragment image. In Proc. 6th Asian Conference on Pattern Recognition 3–15 (2021).10.1007/978-3-031-02444-3_1 ↗
6. Shih, H.-C., Ma, C.-H. & Lu, C.-L. An efficient fragment reconstruction using ransac algorithm. In Proc. IEEE 8th Global Conference on Consumer Electronics 529–530 (2019).10.1109/GCCE46687.2019.9015254 ↗
7. Gwo, C.-Y., Wei, C.-H. & Deng, A.-W. Matching of feature points for moneynote fragment assembly. In Proc. 2nd International Conference on Information Science and Control Engineering 293–296 (2015).10.1109/ICISCE.2015.72 ↗
8. da Gama Leitao, H. C. & Jorge, S. A multiscale method for the reassembly of two-dimensional fragmented objects. IEEE Trans. Pattern Anal. Mach. Intell. 24, 1239–1251 (2002).10.1109/TPAMI.2002.1033215 ↗
9. Wu, Y.-G., Li, X. & Li, M.-Q. Color and contour-based reconstruction of fragmented image. In Proc. International Conference on Computer Science & Education 999–1003 (2013).10.1109/ICCSE.2013.6554059 ↗
10. Kamran, H., Zhang, K., Li, M.-Q. & Li, X. An lcs-based 2d fragmented image reassembly algorithm. In Proc. 13th International Conference on Computer Science & Education 1–6 (2018).10.1109/ICCSE.2018.8468808 ↗
11. Zhang, M. et al. Fast algorithm for 2d fragment assembly based on partial EMD. Vis. Comput. 33, 1601–1612 (2017).10.1007/s00371-016-1303-3 ↗
12. Cecilia, O. & Marie, B.-A. Matching ostraca fragments using a siamese neural network. Pattern Recognit. Lett. 131, 336–340 (2020).10.1016/j.patrec.2020.01.012 ↗
13. Cecilia, O. & Marie, B.-A. Using graph neural networks to reconstruct ancient documents. In Proc. 25th International Conference on Pattern Recognition Workshops 1–16. https://arxiv.org/pdf/2011.07048.pdf (2020).
14. Zhang, Q.-F., Li, L., Fang, R.-R. & Xin, H.-M. Reassembly of two-dimensional irregular fragments by improved polygon feature matching. In Proc. 11th International Conference on Advanced Infocomm Technology 82–85 (2019).10.1109/ICAIT.2019.8935911 ↗
15. Liu, W., Wang, J.-M. & Liu, K.-Q. Longitudinal shredded paper stitching method based on edge matching. Comput. Modern. 02, 55–59 (2019).
16. Lin, H.-Y. & Wen-Cheng, F.-C. Reconstruction of shredded document based on image feature matching. Expert Syst. Appl. 39, 3324–3332 (2012).10.1016/j.eswa.2011.09.019 ↗
17. Ngo, T. T., Nguyen, C. T. & Nakagawa, M. A siamese network-based approach for matching various sizes of excavated wooden fragments. In Proc. 17th International Conference on Frontiers in Handwriting Recognition 307–312 (2020).10.1109/ICFHR2020.2020.00063 ↗
18. Paumard, M.-M., Picard, D. & Tabia, H. Deepzzle: solving visual jigsaw puzzles with deep learning and shortest path optimization. IEEE Trans. Image Process. 29, 3569–3581 (2020).10.1109/TIP.2019.2963378 ↗
19. Paumard, M.-M., Picard, D. & Tabia, H. Image reassembly combining deep learning and shortest path problem. In Proc. European Conference on Computer Vision 1–13. http://arxiv.org/pdf/1809.00898v1.pdf (2018).
20. Cho, T. S., Avidan, S. & Freeman, W. T. A probabilistic image jigsaw puzzle solver. In Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 183–190 (2010).10.1109/CVPR.2010.5540212 ↗
21. Pomeranz, D., Shemesh, M. & Ben-Shahar, O. A fully automated greedy square jigsaw puzzle solver. In Proc. Computer Vision and Pattern Recognition 9–16 (2011).10.1109/CVPR.2011.5995331 ↗
22. Le, C.-Y. & Li, X. Jigsawnet: shredded image reassembly using convolutional neural network and loop-based composition. IEEE Trans. Image Process. 28, 4000–4015 (2019).10.1109/TIP.2019.2903298 ↗
23. Wang, M. & Deng, W.-H. A dataset of Oracle characters for benchmarking machine learning algorithms. Sci. Data 11 (2023).10.1038/s41597-024-02933-w ↗
24. Zhang, C.-S. 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 4482–4492 (2022).10.1145/3534678.3539050 ↗
25. Jin, Y. & Yang, X. Interactively rejoining 2d oracle bone fragments based on contour matching. In Proc. 9th International Conference on Virtual Reality 3–15 (2023).10.1109/ICVR57957.2023.10169751 ↗
26. He, J.-J. et al. Research on rejoining bone stick fragment images: a method based on multi-scale feature fusion siamese network guided by edge contour. Appl. Sci. 14, 717 (2024).10.3390/app14020717 ↗
27. Liu, C.-C. et al. Image stitching method of bone stick fragment based on similarity Freeman code matching. IEEE Access 11, 23073–23084 (2023).10.1109/ACCESS.2023.3252894 ↗
28. Jiang, Y., Chen, S.-x, Gao, W.-Z., Peng, M.-L. & Jiang, L.-H. Sff-siam: a new oracle bone rejioning method based on siamese network. IEEE Comput. Graph. Appl. 43, 22–3222–32 (2023).
29. Song, Z.-H. The Collection of Oracle Bones from the Institute of History, Chinese Academy of Social Sciences (Shanghai Ancient Books Publishing House, 2011).
30. Li, Z.-S. & Ge, Y.-H. Peking University Treasures Oracle Bone Inscriptions (Shanghai Ancient Books Publishing House, 2008).
31. Song, Z.-H. Oracle Bone Collections In Lvshun Museum (Shanghai Ancient Books Publishing House,2014).
32. Matsumaru, M. Oracle Bone Inscriptions Collections In Institute of Oriental Culture at the University of Tokyo (Tokyo University Press, 1983).
33. Liu, G.-Q., Yang, Y.-P., Li, X.-S., Ru, L.-Y. & Han, Y.-B. Gca-pvt-net: group convolutional attention and pvt dual-branch network for oracle bone drill chisel segmentation. Herit. Sci. 12, 1–18 (2024).10.1186/s40494-024-01378-z ↗
34. Hu, Q.-Y. et al. Sgrgan: Sketch-guided restoration for traditional Chinese landscape paintings. Herit. Sci. 12, 1–18 (2024).10.1186/s40494-024-01253-x ↗