Author:
Yuan Jiang,Chen Shanxiong,Mo Bofeng,Ma Yuqi,Zheng Wenjun,Zhang Chongsheng
Abstract
AbstractFont classification of oracle bone inscriptions serves as a crucial basis for determining the historical period to which they belong and holds significant importance in reconstructing significant historical events. However, conventional methods for font classification in oracle bone inscriptions heavily rely on expert knowledge, resulting in low efficiency and time-consuming procedures. In this paper, we proposed a novel recurrent graph neural network (R-GNN) for the automatic recognition of oracle bone inscription fonts. The proposed method used convolutional neural networks (CNNs) to perform local feature extraction and downsampling on oracle bone inscriptions. Furthermore, it employed graph neural networks (GNNs) to model the complex topologiure and global contextual information of oracle bone inscriptions. Finally, we used recurrent neural networks (RNNs) to effectively combine the extracted local features and global contextual information, thereby enhancing the discriminative power of the R-GNN. Extensive experiments on our benchmark dataset demonstrate that the proposed method achieves a Top-1 accuracy of 88.2%, significantly outperforming the competing approaches. The method presented in this paper further advances the integration of oracle bone inscriptions research and artificial intelligence. The code is publicly available at: https://github.com/yj3214/oracle-font-classification.
Publisher
Springer Science and Business Media LLC
Reference35 articles.
1. Guo Z, Zhou Z, Liu B, Li L, Jiao Q, Huang C, Zhang J. An improved neural network model based on inception-v3 for oracle bone inscription character recognition. Sci Program. 2022;2022:1–8.
2. Zhang C, Wang B, Chen K, Zong R, Mo B-f, Men Y, Almpanidis G, Chen S, Zhang X. Data-Driven Oracle Bone Rejoining: A Dataset and Practical Self-Supervised Learning Scheme. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022;pp. 4482–4492.
3. Gao F, Zhang J, Liu Y, Han Y. Image translation for oracle bone character interpretation. Symmetry. 2022;14:743.
4. Gao W, Chen S, Zhang C, Mo B, Liu X. OBM-CNN: a new double-stream convolutional neural network for shield pattern segmentation in ancient oracle bones. Appl Intell. 2022;52:12241–57.
5. Wang M, Deng W, Liu C-L. Unsupervised structure-texture separation network for oracle character recognition. IEEE Trans Image Process. 2022;31:3137–50.
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献