Zhaochen Lyu
ABSTRACT
Oracle bone inscriptions (OBIs) are the earliest Chinese writing system. However, deciphering OBIs is a very challenging task because of the lack of data and time- and resource-consuming manual classification process. In this paper, I apply the technology of deep learning to solve the problem of OBI recognition, proposing a method for merging incompatible OBI classification datasets and implementing it successfully, significantly raising the training and testing accuracy of the neural networks tested. Another major contribution of this paper is the inclusion of a residual module on the AlexNet convolutional neural network, which achieves an accuracy of 89.51% after hyperparameter optimization on the merged dataset, about 1% better than the classical AlexNet under the same conditions and meets the expectation.
- [1] Wang Xiao, Observing Divination in the Shang Dynasty through OBIs in Yinxu [in Chinese]Google Scholar
- [2] Cheung C. The Chinese History That Is Written in Bone. https://www.sapiens.org/archaeology/chinese-oracle-bones-history/. Accessed 2021.5.21.Google Scholar
- [3] Ma Chang, Cao Kun. ”Letter of celebration of the 120th Anniversary of the Discovery and Research on OBIs from Xi Jinping.” people.cn, People’s Daily [in Chinese]Google Scholar
- [4] Yin Cuixue. Study of School Education in the Yin-Shang Dynasty Based on OBIs, East China Normal University, 2019 [in Chinese]Google Scholar
- [5] Gu Shaotong, OBI Recognition Method Based on Topological Registration, Computer and Mathematical Engineering [in Chinese]Google Scholar
- [6] Gu Xuzheng, Cai Hengjin, Lin Li. OBI radicals Recognition Method Based on Capsule Network. Intelligent Systems Journal, 2020 [in Chinese]Google Scholar
- [7] Y. Zhang, H. Zhang, Y. Liu, Q. Yang, C. Liu. Oracle Character Recognition by Nearest Neighbor Classification with Deep Metric Learning. 2019 International Conference on Document Analysis and Recognition (ICDAR), 2019.Google ScholarCross Ref
- [8]Chen Shanxiong, Mo Bofeng, Han Xu, Gao Weizhe, Liu Xuxing. A Classification Method of Oracle Materials Based on Local Convolutional Neural Network Framework. IEEE computer graphics and applications, 2020.Google Scholar
- [9] Han X, Bai Y, K Qiu, et al. IsOBS: An Information System for Oracle Bone Script. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 2020.Google Scholar
- [10] OBC306 Dataset. http://jgw.aynu.edu.cn/ajaxpage/home2.0/DataOBC/detail.html?sysid=20. Accessed 2021.8.28.Google Scholar
- [11] Wang Haobin. Study on OBI Detection and Recognition Based on Deep Learning, South China University of Technology, 2019 [in Chinese]Google Scholar
- [12] Liu Guoying. OBI Character Detection and Recognition based on Deep Learning. Yindu Journal, 2020.Google Scholar
- [13] Fu Panpan, Si Qi, Wang Xinsai. Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice. Computer Programming Skills and Maintenance, 2020Google Scholar
- [14] Takuya A., Shotaro S., Toshihiko Y., Takeru O., Masanori K. Optuna: A Next-generation Hyperparameter Optimization Framework. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD) ’19. 2019.Google Scholar
- [15] scikit-optimize: Sequential model-based optimization in Python. https://scikit-optimize.github.io/stable/. Accessed 2021.6.19.Google Scholar
- [16] Hyperopt: Distributed Hyperparameter Optimization. https://github.com/hyperopt/hyperopt. Accessed 2021.6.19.Google Scholar
- [17] Liaw, R., Liang, E., Nishihara, R., Moritz, P., Gonzalez, J. E., Stoica, I. Tune: A research platform for distributed model selection and training. 2018.Google Scholar
Index Terms
- Automated Recognition of Oracle Bone Inscriptions Using Deep Learning and Data Augmentation
Recommendations
Dynamic Dataset Augmentation for Deep Learning-based Oracle Bone Inscriptions Recognition
Oracle bone inscriptions (OBIs) are a kind of hieroglyph, used about 3,600 years ago for divination and the recording of events. The characters on these OBIs are of great interest because they are precursors to the modern Chinese characters widely used ...
Sundial-GAN: A Cascade Generative Adversarial Networks Framework for Deciphering Oracle Bone Inscriptions
MM '22: Proceedings of the 30th ACM International Conference on MultimediaOracle Bone Inscription (OBI) is an early hieroglyph in China, which is the most famous ancient writing system in the world. However, only a small number of OBI characters have been fully deciphered today. Chinese characters have different forms in ...
Deciphering Ancient Chinese Oracle Bone Inscriptions Using Case-Based Reasoning
Case-Based Reasoning Research and DevelopmentAbstractAncient oracle bone inscriptions (OBIs) are important Chinese cultural artefacts, which are difficult and time-consuming to decipher even by the most expert paleographers and, as a result, a large proportion of excavated OBIs remain unidentified. ...
Comments