Abstract
Research on oracle bone inscription image retrieval is important for applications in academic and cultural heritage areas. The current oracle bone dataset faces problems such as the low similarity between the same category, the high similarity between the different categories, and imbalanced sample distribution. In addition, due to the complex background of oracle bone images, existing network models have certain limitations in extracting image features. To address these challenges, this study first adopts a Siamese network-based image retrieval method to learn feature representations of similar and dissimilar images. Subsequently, the existing dataset was partitioned, providing a practical and usable retrieval dataset for the oracle bone image retrieval field. Finally, an improved network model based on ResNet is proposed and integrated into the Siamese network framework. The model achieves the highest retrieval MP and MAP values of 83.26% and 90.68%, respectively, which is better than the current research.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
H. Zhan and Y. Qi, Chinese character image retrieval based on moment invariants and shape context. 2015 IEEE International Conference on Computer and Communications (ICCC), Chengdu, China, 2015, pp. 146-150
S. Huang, H. Wang, Y. Liu, X. Shi, and L. Jin, OBC306: A Large-Scale Oracle Bone Character Recognition Dataset. 2019 International Conference on Document Analysis and Recognition (ICDAR), Sydney, NSW, Australia, 2019, pp. 681-688
Q. Zhang, Z. Wang, X. Hu, and R. Chen, A Content-Based Image Retrieval Scheme for Encrypted Domain Using Feature Fusion Deep Supervised Hash. 2023 IEEE International Conference on Sensors, Electronics and Computer Engineering (ICSECE), Jinzhou, China, 2023, pp. 34-39
Jing, X., Gao Feng, W., Qinxia,: Research on Semantic Mining for Large-scale Oracle Bone Inscriptions Foundation Data. New Technology of Library and Information Service 31(2), 7–14 (2015)
T. Lin, Method of oracle bone inscription image retrieval based on Siamese neural network(in Chinese). Xiamen University, 2020
Liu, G., Wang, Y.: Oracle character image retrieval by combining deep neural networks and clustering technology. Int. J. Comput. Sci. 2, 199–206 (2015)
Han X, Bai Y, Qiu K, et al, IsOBS: An information system for oracle bone script. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demon- stations. Association for Computational Linguistics, 2020: 227-233
Zhixi.Yao, Research on Oracle Bone Script Image Recognition and Retrieval Based on Multi-Strategy Enhancement(in Chinese). Xinjiang University, 2022
K. R. N. Aswini, S. P. Prakash, G. Ravindran, T. Jagadesh and A. V. Naik, An Extended Canberra Similarity Measure Method for Content-Based Image Retrieval. 2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques (EASCT), Bengaluru, India, 2023, pp. 1-5
Kumar, G.V.R.M., Madhavi, D.: Stacked Siamese Neural Network (SSiNN) on Neural Codes for Content-Based Image Retrieval. IEEE Access 11, 77452–77463 (2023)
Sumbul, G., Ravanbakhsh, M., Demir, B., Relevant, A., Hard and Diverse Triplet Sampling Method for Multi-Label Remote Sensing Image Retrieval.: IEEE Mediterranean and Middle-East Geoscience and Remote Sensing Symposium (M2GARSS). Istanbul, Turkey 2022, 5–8 (2022)
N. Carlevaris-Bianco and R. M. Eustice, Learning visual feature descriptors for dynamic lighting conditions. 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, Chicago, IL, USA, 2014, pp. 2769-2776
Z. Pan, X. Bao, Y. Zhang, B. Wang, Q. An, and B. Lei, Siamese Network-Based Metric Learning for SAR Target Classification. IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan, 2019, pp. 1342-1345
F. Radenović, G. Tolias, and O. Chum, Fine-Tuning CNN Image Retrieval with No Human Annotation. in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 7, pp. 1655-1668, 1 July 2019
Razavian A S, Sullivan J, Maki A, et al, A Baseline for Visual Instance Retrieval with Deep Convolutional Networks.ITE Transactions on Media Technology and Applications, 2014, 4(3)
Chicco, D. (2021). Siamese Neural Networks: An Overview. In: Cartwright, H. (eds) Artificial Neural Networks. Methods in Molecular Biology, vol 2190. Humana, New York, NY
Linchang Zhao, Zhaowei Shang, et al, Siamese networks with an online reweighted example for imbalanced data learning, Pattern Recognition, Volume 132,2022
Yafei MAO, BI Xiaojun. Rubbing oracle bone character recognition based on improved ResNeSt network. CAAI Transactions on Intelligent Systems, 2023, 18(3): 450-458
Zhang, Y.-K., Zhang, H., Liu, Y.-G., et al.: Oracle character recognition based on cross-modal deep metric learning. Acta Automatica Sinica 47(4), 791–800 (2021)
K. He, X. Zhang, S. Ren and J. Sun, Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 770-778
C. Szegedy, V. Vanhoucke, S. Ioffe, et al, Rethinking the Inception Architecture for Computer Vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 2818-2826
Shen, Y. et al. (2020). Enabling Deep Residual Networks for Weakly Supervised Object Detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science, vol 12353. Springer, Cham
Huang, G., Liu, Z.: Maaten L D, et al, Densely connected convolutional networks. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017, 2261–2269 (2017)
Christopher D, Manning P R, Schutze H. Introduction to information retrieval. Cambridge University Press, 2008
Harbin Wang, Research on Oracle Bone Script Detection and Recognition Based on Deep Learning(in Chinese). South China University of Technology, 2019
Acknowledgements.
This study was Supported by the National Natural Science Foundation of China(NO.62266044,62061045). It was also supported by the "Tianshan Talents" Leading Talents Program for Scientific and Technological Innovation in Xinjiang Uygur Autonomous Region (2023TSYCLJ0025), and the Open Project of Key Laboratory of Oracle Bone Inscription Information Processing, Ministry of Education (OIP2021E004).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ding, J., Wang, J., Aysa, A., Xu, X., Ubul, K. (2025). Oracle Bone Inscription Image Retrieval Based on Improved ResNet Network. In: Antonacopoulos, A., Chaudhuri, S., Chellappa, R., Liu, CL., Bhattacharya, S., Pal, U. (eds) Pattern Recognition. ICPR 2024. Lecture Notes in Computer Science, vol 15321. Springer, Cham. https://doi.org/10.1007/978-3-031-78305-0_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-78305-0_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-78304-3
Online ISBN: 978-3-031-78305-0
eBook Packages: Computer ScienceComputer Science (R0)