中
Personal Profile

Paper Publications

Current position: Home > Scientific Research > Paper Publications

Improving Oracle Bone Characters Recognition via A CycleGAN-Based Data Augmentation Method

Release Time:2026-06-30
Hits:
Date:
2026-06-30
Institution:
人工智能教育学部
Title of Paper:
Improving Oracle Bone Characters Recognition via A CycleGAN-Based Data Augmentation Method
Journal:
国际计算机前沿大会会议论文集
Place of Publication:
国内外公开发行
Key Words:
Learning algorithms
Summary:
Oracle bone inscription is the earliest writing system in China which contains rich information about the history of Shang dynasty. Automatically recognizing oracle bone characters is of great significance since it could promote the research on history, philology and archaeology. The proposed solutions for oracle bone characters recognition are mainly based on machine learning or deep learning algorithms which rely on a large number of supervised training data. However, the existing dataset suffers from the problem of severe class imbalance. In this work, we propose a CycleGAN-based data augmentation method to overcome the limitation. Via learning the mapping between the glyph images data domain and the real samples data domain, CycleGAN could generate oracle character images of high-quality. The quality is evaluated using the quantitative measure. Totally, 185362 samples are generated which could serve as a complementary to the existing dataset. With these generated samples, the state of the art results of recognition task on OBC306 are improved greatly in terms of mean accuracy and total accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Co-author:
Zhao, Yiwen,Jin, Xinxin,Mouchere, Harold,余新国
First Author:
王伟
Correspondence Author:
张婷
Document Code:
1722785276637614080
Document Type:
00013
Volume:
1793 CCIS
ISSN:
1865-0929
Translation or Not:
No
Date of Publication:
2023-04-01
Included Journals:
其他(ESI、Scopus、OA)、EI