TD-Net:tiny defect detection network for industrial products
Complex & Intelligent Systems · 2024-06 · 10 (3) · 3943-3954
DOI: 10.1007/s40747-024-01362-x ↗Kurz gefasst
Fachartikel in der Zeitschrift Complex & Intelligent Systems, online erschienen am 29.02.2024. Verfasst von Rui Shao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 42-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Taishan Scholars Program, Key R &D Program of Shandong Province, China.
Abstract (Originalsprache)
The detection of tiny defects in industrial products is important for improving the quality of industrial products and maintaining production safety. Currently, image-based defect detection methods are ineffective in detecting tiny and variously shaped defects. Therefore, this paper proposes a tiny defect detection network (TD-Net) for industrial products to improve the effectiveness of tiny defect detection. TD-Net improves the overall defect detection effect, especially the detection effect of tiny defects, by solving the problems of downsampling of tiny defects, pre-filtering of conflicting deep and shallow semantic information, and cascading fusion of multi-scale information. Specifically, this paper proposes the Defect Downsampling (DD) module to realize the defect information supplementation during the backbone downsampling process and improve the problem that the stepwise convolution easily misses the detection of tiny defects. Meanwhile, the Semantic Information Interaction Module (SIIM) is proposed, which fuses deep and shallow semantic features, and is designed to interact the fused features with shallow features to optimize the detection of tiny defects. Finally, the Scale Information Fusion Module (SIFM) is proposed to improve the Path Aggregation Network (PANet) for cascading fusion and information focus on different scale information, which enables further improvement of defect detection performance of TD-Net. Extensive experimental results on the NEU–DET data set (76.8 $$\%$$ % mAP), the Peking University PCB defect data set (96.2 $$\%$$ % mAP) and the GC10-DET data set (71.5 $$\%$$ % mAP) show that the proposed TD-Net achieves competitive results compared with SOTA methods with the equivalent parameter quantity.
Förderung
- the Taishan Scholars Program
- Key R &D Program of Shandong Province, China
Zitieren
APA
Shao, R., Zhou, M., Li, M., Han, D., & Li, G. (2024). TD-Net:tiny defect detection network for industrial products. Complex & Intelligent Systems, 10(3), 3943-3954. https://doi.org/10.1007/s40747-024-01362-x
Vancouver
Shao R, Zhou M, Li M, Han D, Li G. TD-Net:tiny defect detection network for industrial products. Complex & Intelligent Systems. 2024;10(3):3943-3954. doi:10.1007/s40747-024-01362-x
BibTeX
@article{Shao2024,
author = {Shao, Rui and Zhou, Mingle and Li, Min and Han, Delong and Li, Gang},
title = {TD-Net:tiny defect detection network for industrial products},
journal = {Complex & Intelligent Systems},
year = {2024},
volume = {10},
number = {3},
pages = {3943--3954},
doi = {10.1007/s40747-024-01362-x}
}
EUVIMED