SCT-YOLO: A Dual-Stream Defect Detection Network Utilizing Computational Shape, Texture, and Color Features
Sensors · 08.06.2026 · 26 (12) · 3662
DOI: 10.3390/s26123662 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 08.06.2026. Verfasst von Zhenning Mou und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical Engineering, Suzhou University of Science and Technology, No. 55, Changjiang Road, Suzhou 215009, China. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jiangsu Education Department, National Natural Science Foundation of China, Jiangsu Innovation and Entrepreneurship Team.
Abstract (Originalsprache)
Steel surface defect detection is a key component of industrial quality control. Existing deep learning methods mostly rely on single-backbone networks to extract high-level semantic features from raw images, yet fail to explicitly analyze low-level visual features. To overcome the limitations of conventional frameworks, this paper proposes SCT-YOLO, a defect detection model based on a dual-stream collaborative architecture that effectively integrates low-level visual features with high-level semantic information for complementary feature representation. The primary scientific novelty of this work lies in the formalization of a multi-dimensional prior feature-guided learning paradigm, which mathematically bridges explicit hand-crafted physical priors with deep latent representations within this dual-stream architecture, differing from conventional black-box deep feature extraction. On the SD-Saliency-900 dataset, the proposed SCT-YOLO achieves an mAP@0.5 of 88.9%, representing a significant 4.6% improvement over the baseline model YOLOv8n, while maintaining an inference speed of 257.2 FPS with only 5.66 M parameters and 15.2 GFLOPs, fully meeting the real-time deployment requirements of industrial production lines. Visualization analysis demonstrates that the method exhibits more stable detection capability for small defects in complex backgrounds. Meanwhile, experiments on the GC10-DET dataset further verify its excellent generalization performance, providing a reliable technical solution for other industrial defect detection scenarios.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Mechanical Engineering, Suzhou University of Science and Technology, No. 55, Changjiang Road, Suzhou 215009, China.
- School of Advanced Technology, Xi'an Jiaotong-Liverpool University, No. 111, Ren'ai Road, Suzhou 215123, China.
- School of Electronic & Information Engineering, Suzhou University of Science and Technology, No. 99, Xuefu Road, Suzhou 215009, China.
ORCID-Profile: Zhenning Mou, Yuchao Dai, Yehu Shen, Guizhong Fu
Förderung
- Jiangsu Education Department
- National Natural Science Foundation of China
- Jiangsu Innovation and Entrepreneurship Team
Zitieren
APA
Mou, Z., Dai, Y., Cao, Z., Lv, Z., Wang, L., Shen, Y., & Fu, G. (2026). SCT-YOLO: A Dual-Stream Defect Detection Network Utilizing Computational Shape, Texture, and Color Features. Sensors, 26(12), 3662. https://doi.org/10.3390/s26123662
Vancouver
Mou Z, Dai Y, Cao Z, Lv Z, Wang L, Shen Y, et al. SCT-YOLO: A Dual-Stream Defect Detection Network Utilizing Computational Shape, Texture, and Color Features. Sensors. 2026;26(12):3662. doi:10.3390/s26123662
BibTeX
@article{Mou2026,
author = {Mou, Zhenning and Dai, Yuchao and Cao, Zihe and Lv, Zhe and Wang, Lei and Shen, Yehu and Fu, Guizhong},
title = {SCT-YOLO: A Dual-Stream Defect Detection Network Utilizing Computational Shape, Texture, and Color Features},
journal = {Sensors},
year = {2026},
volume = {26},
number = {12},
pages = {3662},
doi = {10.3390/s26123662}
}
EUVIMED