Optimizing surface defect detection with YOLOv9: the role of advanced backbone models
The study offers practical guidance for backbone selection in surface defect detection tasks, highlighting the advantages of lightweight architectures for real-time industrial applications.
Authors
- Chi Yao (ORCID: https://orcid.org/0000-0001-9307-9085)
- Shi‐Min Cai (ORCID: https://orcid.org/0000-0002-2089-5150)
- Hongyang Wang (ORCID: https://orcid.org/0000-0003-4110-7034)
- Zhuo Zeng (ORCID: https://orcid.org/0000-0003-4107-0622)
- Zhaohui Dong (ORCID: https://orcid.org/0000-0002-6388-6879)
Institutions
- Northeastern University (US)
- University of Electronic Science and Technology of China (CN)
Publication Details
- Journal
- Frontiers in Artificial Intelligence
- Published
- 2025-10-10
- DOI
- https://doi.org/10.3389/frai.2025.1675154
- Citations
- 1
- Primary Topic
- Industrial Vision Systems and Defect Detection
- Type
- article
- Field-Weighted Citation Impact
- 1.24
Funders
- Chengdu Science and Technology Bureau