R-GNN: recurrent graph neural networks for font classification of oracle bone inscriptions
Abstract Font 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 inscrip...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-01-01
|
| Series: | Heritage Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40494-024-01133-4 |
| _version_ | 1797273629013049344 |
|---|---|
| author | Jiang Yuan Shanxiong Chen Bofeng Mo Yuqi Ma Wenjun Zheng Chongsheng Zhang |
| author_facet | Jiang Yuan Shanxiong Chen Bofeng Mo Yuqi Ma Wenjun Zheng Chongsheng Zhang |
| author_sort | Jiang Yuan |
| collection | DOAJ |
| description | Abstract Font 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 . |
| first_indexed | 2024-03-07T14:47:08Z |
| format | Article |
| id | doaj.art-e5d74342f7894f7ab684c89480b8ef30 |
| institution | Directory Open Access Journal |
| issn | 2050-7445 |
| language | English |
| last_indexed | 2024-03-07T14:47:08Z |
| publishDate | 2024-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Heritage Science |
| spelling | doaj.art-e5d74342f7894f7ab684c89480b8ef302024-03-05T19:55:35ZengSpringerOpenHeritage Science2050-74452024-01-0112111410.1186/s40494-024-01133-4R-GNN: recurrent graph neural networks for font classification of oracle bone inscriptionsJiang Yuan0Shanxiong Chen1Bofeng Mo2Yuqi Ma3Wenjun Zheng4Chongsheng Zhang5College of Computer and Information Science, Southwest UniversityCollege of Computer and Information Science, Southwest UniversityThe Center for Oracle Bone Studies, Capital Normal UniversityCollege of Computer and Information Science, Southwest UniversityCollege of Computer and Information Science, Southwest UniversitySchool of Computer and Information Engineering, Henan UniversityAbstract Font 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 .https://doi.org/10.1186/s40494-024-01133-4Oracle bone inscriptionsDeep learningFont classificationRecurrent graph neural network |
| spellingShingle | Jiang Yuan Shanxiong Chen Bofeng Mo Yuqi Ma Wenjun Zheng Chongsheng Zhang R-GNN: recurrent graph neural networks for font classification of oracle bone inscriptions Heritage Science Oracle bone inscriptions Deep learning Font classification Recurrent graph neural network |
| title | R-GNN: recurrent graph neural networks for font classification of oracle bone inscriptions |
| title_full | R-GNN: recurrent graph neural networks for font classification of oracle bone inscriptions |
| title_fullStr | R-GNN: recurrent graph neural networks for font classification of oracle bone inscriptions |
| title_full_unstemmed | R-GNN: recurrent graph neural networks for font classification of oracle bone inscriptions |
| title_short | R-GNN: recurrent graph neural networks for font classification of oracle bone inscriptions |
| title_sort | r gnn recurrent graph neural networks for font classification of oracle bone inscriptions |
| topic | Oracle bone inscriptions Deep learning Font classification Recurrent graph neural network |
| url | https://doi.org/10.1186/s40494-024-01133-4 |
| work_keys_str_mv | AT jiangyuan rgnnrecurrentgraphneuralnetworksforfontclassificationoforacleboneinscriptions AT shanxiongchen rgnnrecurrentgraphneuralnetworksforfontclassificationoforacleboneinscriptions AT bofengmo rgnnrecurrentgraphneuralnetworksforfontclassificationoforacleboneinscriptions AT yuqima rgnnrecurrentgraphneuralnetworksforfontclassificationoforacleboneinscriptions AT wenjunzheng rgnnrecurrentgraphneuralnetworksforfontclassificationoforacleboneinscriptions AT chongshengzhang rgnnrecurrentgraphneuralnetworksforfontclassificationoforacleboneinscriptions |