Abstract
Image based object fragments rejoining can avoid touching and damaging objects, and be applied to recover fragments of oracle bones, artifacts, paper money, calligraphy and painting files. However, traditional methods are insufficient in terms of judging whether two images’ texture are rejoinable. In this paper, we propose a deep rejoining model (DRM) for automatic rejoining of oracle bone fragment images. In our model, an edge equal distance rejoining method (EEDR) is used to locate the matching position of the edges of two fragment images and crop the target area image (TAI), then a convolution neural network (CNN) is used to evaluate the similarity of texture in TAI. To improve the performance of similarity evaluation, a maximum similarity pooling (MSP) layer is proposed in CNN, and the fully connected layer outputs the two-class probability of whether the rejoining is eligible or not. Our experiments show that DRM achieved state-of-the-arts performance in rejoining oracle bone fragment images and has stronger adaptability.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chou, H., Opstad, D.: Computer matching of oracle bone fragments: a preliminary report on a new research method. Archaeology 26(33), 176–181 (1973)
Tong, E., Zhang, S., Cheng, J.: Preliminary report on the use of computers to rejoin fragments of Shang Daibujia. J. Sichuan Univ. (Nat. Sci. Edn.) 2, 57–65 (1975)
Zhang, C., Wang, A.: A computer-aided oracle bone inscription rubbing conjugation method. Electron. Design Eng. 20(17), 1–3 (2012)
Liu, Y., Wang, T., Wang, J.: The application of the technique of 2D fragments stitching based on outline feature in rejoining oracle bones. In: International Conference on Multimedia Information Networking and Security, pp. 964–968 (2010)
Wang, A., Liu, G., Ge, W., et al.: Oracle computer-aided conjugation system design. Comput. Eng. Appl. 46(21), 59–62 (2010)
Tublee, E., Rabaud, V., Konolige, K., Bradski, G.: ORB: an efficient alternative to SIFT or SURF. IEEE Int. Conf. Comput. Vis. 58(11), 2564–2571 (2011)
Leutenegger, S., Chli, M.Y., Siegwart, R.: BRISK: binary robust invariant scalable keypoints. IEEE Int. Conf. Comput. Vis. 58(11), 2548–2555 (2012)
Alahi, A., Ortiz, R., Vandergheynst, P.: FREAK: fast retina keypoint. IEEE Conf. Comput. Vis. Pattern Recogn. 157(10), 510–517 (2012)
Zhang, Z., Yang, D., Lian, M.: Circumferential binary feature extraction and matching search algorithms. IEEE Signal Process. Lett. 25(7), 1074–1078 (2018)
Zhang, H., Xue, J., Dana, K.: Deep TEN: texture encoding network. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2896–2905 (2017)
Xue, J., Zhang, H., Dana, K.: Deep texture manifold for ground terrain recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 558–567 (2018)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation Tech report. In: IEEE International Conference on Computer Vision, pp. 580–587 (2014)
Girshick, R.: Fast R-CNN. In: IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2017)
He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 386–397 (2020)
Szegedy, C., Liu, W., Jia, Y., et al.: A going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
Szegedy, C., Vanhoucke, V., Ioffe, S., et al.: Rethinking the inception architecture for computer vision. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception–V4, inception – ResNet and the impact of residual connections on learning. In: The 31th AAAI Conference on Artificial Intelligence, pp. 4278–4284 (2016)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Ruiz, L., Gama, F., Marques, A.G., Ribeiro, A.: Invariance-preserving localized activation functions for graph neural networks. IEEE Trans. Signal Process. 68, 127–141 (2020)
Cao, W., Yan, Z., He, Z., et al.: A comprehensive survey on geometric neural networks. IEEE Access 8, 35929–35949 (2020)
Lin, Y.: Exploiting Information Science Technology to Rejoin An-yang Oracle bones/Shells, pp. 32–41. Tsinghua University, Taiwan (2006)
Zhang, Z., Yang, D.: Internal and external similarity aggregation stereo matching algorithm. In: The 11th International Conference on Digital Image Processing, vol. 11179, p. 62 (2019)
Mei, X., Sun, X., Dong, W., Wang, H., et al.: Segment-tree based cost aggregation for stereo matching. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 313–320 (2013)
Acknowledgements
This work has been supported by the National Natural Science Foundation of China (62106007, 61806007), Department of Science and Technology of Henan Province (212102310549) and Anyang Normal University Science and Technology Research Project (2021C01GX012).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, Z., Wang, YT., Li, B., Guo, A., Liu, CL. (2022). Deep Rejoining Model for Oracle Bone Fragment Image. In: Wallraven, C., Liu, Q., Nagahara, H. (eds) Pattern Recognition. ACPR 2021. Lecture Notes in Computer Science, vol 13189. Springer, Cham. https://doi.org/10.1007/978-3-031-02444-3_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-02444-3_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-02443-6
Online ISBN: 978-3-031-02444-3
eBook Packages: Computer ScienceComputer Science (R0)