MSFE-YOLO: A Steel Surface Defect Detection Algorithm Integrating Multi-Scale Frequency Domain and Defect-Aware Attention
Sensors · 09.04.2026 · 26 (8) · 2311
DOI: 10.3390/s26082311 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 09.04.2026. Verfasst von Siqi Su und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical and Energy Engineering, Guangdong Ocean University, Yangjiang 529500, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, the State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing Uni-versity, Zhanjiang Science and Technology Planning Project.
Abstract (Originalsprache)
Detecting surface defects on steel products is crucial for maintaining quality standards in industrial manufacturing. However, existing detection algorithms face several challenges, including the difficulty of capturing multi-scale defect characteristics with fixed receptive fields, insufficient utilization of defect edge and frequency domain features, and simplistic feature fusion strategies. In response to the above challenges, this paper proposed the Multi-Scale Frequency-Enhanced YOLO (MSFE-YOLO) algorithm that integrates multi-scale frequency domain enhancement with defect-aware attention mechanisms. First, a Multi-Scale Frequency-Enhanced Convolution (MSFC) module was constructed, which extracted multi-scale spatial features in parallel through depth-adaptive dilated convolutions, explicitly modeled high-frequency edge information using the Laplacian operator, and achieved adaptive fusion of multi-branch features via learnable weights. Second, a Cross-Stage Partial with Multi-Scale Defect-Aware Attention (C2MSDA) module was designed, integrating Sobel operator-based edge perception, multi-scale spatial attention, and adaptive channel attention to collaboratively enhance features across spatial, channel, and edge domains through a gated fusion strategy. Finally, an Adaptive Feature Fusion Enhancement (AFFE) module was proposed to achieve adaptive aggregation of multi-level features through a data-driven weight generation network and cross-scale feature interaction mechanism. Experimental results on the NEU-DET and GC10-DET datasets demonstrated that MSFE-YOLO achieved the mAP@0.5 of 79.8% and 66.7%, respectively, which were 1.7% and 2.1% higher than the benchmark model YOLOv11s respectively, while maintaining an inference speed of 89.3 FPS, which satisfied the real-time detection requirements in industrial scenarios.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Mechanical and Energy Engineering, Guangdong Ocean University, Yangjiang 529500, China.
- State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing University, Chongqing 400044, China.
Förderung
- National Natural Science Foundation of China
- the State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing Uni-versity
- Zhanjiang Science and Technology Planning Project
- the Program for Scientific Research Start-up Funds of Guangdong Ocean University
- State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing University
- Guangdong Ocean University
Zitieren
APA
Su, S., Shen, J., Lin, P., Tang, W., Zhang, W., & Chen, Z. (2026). MSFE-YOLO: A Steel Surface Defect Detection Algorithm Integrating Multi-Scale Frequency Domain and Defect-Aware Attention. Sensors, 26(8), 2311. https://doi.org/10.3390/s26082311
Vancouver
Su S, Shen J, Lin P, Tang W, Zhang W, Chen Z. MSFE-YOLO: A Steel Surface Defect Detection Algorithm Integrating Multi-Scale Frequency Domain and Defect-Aware Attention. Sensors. 2026;26(8):2311. doi:10.3390/s26082311
BibTeX
@article{Su2026,
author = {Su, Siqi and Shen, Jiale and Lin, Peiyi and Tang, Wanhe and Zhang, Weijie and Chen, Zhen},
title = {MSFE-YOLO: A Steel Surface Defect Detection Algorithm Integrating Multi-Scale Frequency Domain and Defect-Aware Attention},
journal = {Sensors},
year = {2026},
volume = {26},
number = {8},
pages = {2311},
doi = {10.3390/s26082311}
}
EUVIMED