EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Real-Time Defect Detection Model in Industrial Environment Based on Lightweight Deep Learning Network

Jiaqi Lu, Soo-Hong Lee

Electronics · 24.10.2023 · 12 (21) · 4388

DOI: 10.3390/electronics12214388 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 24.10.2023. Verfasst von Jiaqi Lu und 1 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Surface defect detection in industrial environments is crucial for quality management and has significant research value. General detection networks, such as the YOLO series, have proven effective in various dataset detections. However, due to the complex and varied surface defects of industrial products, many defects occupy a small proportion of the surface and fall into the category of typical small target detection problems. Moreover, the complexity of general detection network architectures relies on high-tech hardware, making it difficult to deploy on devices without GPUs or on edge computing and mobile devices. To meet the practical needs of industrial product defect inspection applications, this paper proposes a lightweight network specifically designed for defect detection in industrial fields. This network is composed of four parts: a backbone network, a multiscale feature aggregation network, a residual enhancement network, and an attention enhancement network. The network includes a backbone network that integrates attention layers for feature extraction, a multiscale feature aggregation network for semantic information, a residual enhancement network for spatial focus, and an attention enhancement network for global–local feature interaction. These components enhance detection performance for diverse defects while maintaining low hardware requirements. Experimental results show that this network outperforms the latest and most popular YOLOv5n and YOLOv8n models in the five indicators P, R, F1, mAP@.5, and GFLOPS when used on four public datasets. It even approaches or surpasses the YOLOv8s and YOLOv5s models with several times the GFLOPS computation. It balances the requirements of lightweight real-time and accuracy in the scenario of industrial product surface defect detection.

Zitieren

APA

Lu, J., & Lee, S. (2023). Real-Time Defect Detection Model in Industrial Environment Based on Lightweight Deep Learning Network. Electronics, 12(21), 4388. https://doi.org/10.3390/electronics12214388

Vancouver

Lu J, Lee S. Real-Time Defect Detection Model in Industrial Environment Based on Lightweight Deep Learning Network. Electronics. 2023;12(21):4388. doi:10.3390/electronics12214388

BibTeX
@article{Lu2023,
  author = {Lu, Jiaqi and Lee, Soo-Hong},
  title = {Real-Time Defect Detection Model in Industrial Environment Based on Lightweight Deep Learning Network},
  journal = {Electronics},
  year = {2023},
  volume = {12},
  number = {21},
  pages = {4388},
  doi = {10.3390/electronics12214388}
}
Kostenlos starten →