Bibliographic Details
| Title: |
Glyph graph isomorphism network for structure recognition of oracle bone inscription. |
| Authors: |
Zhang, Zhan1,2 (AUTHOR) zhangzhan@aynu.edu.cn, Liu, Hanbin1 (AUTHOR) liuhanbin@stu.aynu.edu.cn, Zhang, Xingkun1 (AUTHOR) wulizxk@stu.aynu.edu.cn, Wang, Yiyuan3 (AUTHOR) wangyy912@nenu.edu.cn, Gao, Feng1,2 (AUTHOR) gaof@aynu.edu.cn, Guo, An1,2 (AUTHOR) guoan@aynu.edu.cn, Zhang, Han2 (AUTHOR) hanzhang@aynu.edu.cn, Jiao, Qingju1,2 (AUTHOR) qjjiao@aynu.edu.cn, Li, Bang1,2 (AUTHOR) libang@aynu.edu.cn, Liu, Yongge1 (AUTHOR) liuyongge@aynu.edu.cn |
| Source: |
Expert Systems with Applications. Mar2026:Part A, Vol. 298, pN.PAG-N.PAG. 1p. |
| Subjects: |
Graph neural networks, Inscriptions, Chinese history, Feature extraction, Structural analysis (Science) |
| Abstract: |
Structure recognition of oracle bone inscription glyphs plays an important role in studying the evolutionary process of oracle bone inscriptions and the history of the Shang Dynasty. Currently, most methods have decomposed oracle bone inscription glyphs into multilevel features, which are used to recognize hierarchical feature fusion. This strategy cannot recognize the primitive internal structures of keypoints, strokes, and components. Moreover, mainstream graph neural networks cannot fully utilize the rich structural information of oracle bone inscription glyphs, resulting in their inability to meet the needs of structure recognition. So we have developed a graph structure recognition method to implement structure recognition of oracle bone inscription glyphs. A graph extraction method is given to get the structure of oracle bone inscription glyphs; each graph structure's representation vector can be learned by a glyph graph isomorphism network, which is developed to recognize the graph of oracle bone inscription glyphs to enhance the discriminability representation of the structure. Our model has achieved advanced results across structure recognition experiments in the HWOBC dataset and the Oracle-50K dataset. [ABSTRACT FROM AUTHOR] |
|
Copyright of Expert Systems with Applications is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Engineering Source |
