Optimization and Validation of Wafer Surface Defect Detection Algorithm Based on RT-DETR
IEEE Access · 2025 · 13 · 39727-39737
DOI: 10.1109/access.2025.3543525 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2025. Verfasst von Ao Xu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ji Hua Laboratory.
Abstract (Originalsprache)
In response to the issue of poor detection performance on wafer surface defect spots and elongated scratches, an improved RT-DETR method for wafer surface defect detection is proposed. Firstly, a dynamic snake convolutional layer is introduced to detect elongated scratches where conventional convolutional kernels fail to extract features effectively. Secondly, to address the problem of information loss in small targets, an attention-based Transformer encoder module and a feature fusion network based on residual thinking are proposed. Finally, verification is conducted using a wafer test dataset. Experimental results demonstrate that compared to the original RT-DETR method, the model exhibits a 4.1% improvement in detecting small particles and a 5.4% improvement in scratch detection performance. Fully meeting the requirements of intelligent manufacturing and high detection accuracy.
Förderung
- Ji Hua Laboratory
Zitieren
APA
Xu, A., Li, Y., Xie, H., Yang, R., Li, J., & Wang, J. (2025). Optimization and Validation of Wafer Surface Defect Detection Algorithm Based on RT-DETR. IEEE Access, 13, 39727-39737. https://doi.org/10.1109/access.2025.3543525
Vancouver
Xu A, Li Y, Xie H, Yang R, Li J, Wang J. Optimization and Validation of Wafer Surface Defect Detection Algorithm Based on RT-DETR. IEEE Access. 2025;13:39727-39737. doi:10.1109/access.2025.3543525
BibTeX
@article{Xu2025,
author = {Xu, Ao and Li, Yanwei and Xie, Hongbo and Yang, Rui and Li, Jianjie and Wang, Jiaying},
title = {Optimization and Validation of Wafer Surface Defect Detection Algorithm Based on RT-DETR},
journal = {IEEE Access},
year = {2025},
volume = {13},
pages = {39727--39737},
doi = {10.1109/access.2025.3543525}
}
EUVIMED