Enhanced YOLOv8 for industrial polymer films: a semi-supervised framework for micron-scale defect detection
The improved YOLOv8 algorithm meeting the stringent requirements for high-precision small-target defect detection on polymer material film in industrial production. Future work will explore more advanced techniques to enhance model accuracy and robustness.
Authors
- Bin‐Jie Hu (ORCID: https://orcid.org/0000-0002-4716-4649)
- Jian Wan (ORCID: https://orcid.org/0000-0001-5904-9261)
- Xinduoji Yang (ORCID: https://orcid.org/0009-0006-5200-016X)
- Weifeng Jiang
- Xiaoyan Dong (ORCID: https://orcid.org/0000-0001-5314-1542)
- Xiaoxia Yu (ORCID: https://orcid.org/0000-0002-5972-5685)
- Nianbo Liu
Institutions
- University of Electronic Science and Technology of China (CN)
- Quzhou University (CN)
- Dahua Technology (China) (CN)
- Intelligent Health (United Kingdom) (GB)
Publication Details
- Journal
- Frontiers in Artificial Intelligence
- Published
- 2025-09-09
- DOI
- https://doi.org/10.3389/frai.2025.1638772
- Citations
- 1
- Primary Topic
- Industrial Vision Systems and Defect Detection
- Type
- article
- Field-Weighted Citation Impact
- 1.24
Funders
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
- University of Electronic Science and Technology of China
- Natural Science Foundation of Zhejiang Province