Machine vision-based surface defect testing of industrial materials using a lightweight multiscale attention fusion network
Materials Testing · 25.11.2026 · 68 (11) · 2073-2086
DOI: 10.1515/mt-2026-0236 ↗Kurz gefasst
Fachartikel in der Zeitschrift Materials Testing, online erschienen am 23.09.2026. Verfasst von Fumin Wang und 4 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Gefördert von: The Baima Lake Laboratory Joint Funds of the Zhejiang Provincial Natural Science Foundation of China, The National Natural Science Foundation of China.
Abstract (Originalsprache)
Surface defect detection is essential for maintaining quality in industrial products, but in real industrial applications it faces a dilemma among accuracy, processing speed, and model lightweight. To address this challenge, we propose a method named global attention mechanism for deeply separable YOLO (simply denoted as GMD-YOLO) network. It integrates global context and local information in a multi-scale attention fusion module to improve the recognition of small defects, and an enhanced depth separable convolution to reduce computational cost. The model is evaluated in three typical scenarios individually involving pavement, wood surface and steel surface defects. The accuracy, processing speed, and model lightweight are quantitatively analyzed using mean accuracy, frame rate, and floating-point operations, respectively. Results show that GMD-YOLO not only maintains real-time performance but also outperforms the common methods in the YOLO family in all three metrics. High-resolution thermograms reveal the robust decision basis of the model, and ablation experiments confirm the synergistic gain effect between the sub-modules.
Förderung
- The Baima Lake Laboratory Joint Funds of the Zhejiang Provincial Natural Science Foundation of China
- The National Natural Science Foundation of China
Zitieren
APA
Wang, F., Jiang, J., Zhang, K., Wang, Y., & Liu, Y. (2026). Machine vision-based surface defect testing of industrial materials using a lightweight multiscale attention fusion network. Materials Testing, 68(11), 2073-2086. https://doi.org/10.1515/mt-2026-0236
Vancouver
Wang F, Jiang J, Zhang K, Wang Y, Liu Y. Machine vision-based surface defect testing of industrial materials using a lightweight multiscale attention fusion network. Materials Testing. 2026;68(11):2073-2086. doi:10.1515/mt-2026-0236
BibTeX
@article{Wang2026,
author = {Wang, Fumin and Jiang, Jiahao and Zhang, Kuan and Wang, Yangyu and Liu, Yi},
title = {Machine vision-based surface defect testing of industrial materials using a lightweight multiscale attention fusion network},
journal = {Materials Testing},
year = {2026},
volume = {68},
number = {11},
pages = {2073--2086},
doi = {10.1515/mt-2026-0236}
}
EUVIMED