Industrial Product Surface Anomaly Detection with Realistic Synthetic Anomalies Based on Defect Map Prediction
Sensors · 02.01.2024 · 24 (1) · 264
DOI: 10.3390/s24010264 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 02.01.2024. Verfasst von Tao Peng und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical and Control Engineering, Shaanxi University of Science and Technology, Xi'an 710026, China. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The occurrence of anomalies on the surface of industrial products can lead to issues such as decreased product quality, reduced production efficiency, and safety hazards. Early detection and resolution of these problems are crucial for ensuring the quality and efficiency of production. The key challenge in applying deep learning to surface defect detection of industrial products is the scarcity of defect samples, which will make supervised learning methods unsuitable for surface defect detection problems. Therefore, it is a reasonable solution to use anomaly detection methods to deal with surface defect detection. Among image-based anomaly detection, reconstruction-based methods are the most commonly used. However, reconstruction-based approaches lack the involvement of defect samples in the training process, posing the risk of a perfect reconstruction of defects by the reconstruction network. In this paper, we propose a reconstruction-based defect detection algorithm that addresses these challenges by utilizing more realistic synthetic anomalies for training. Our model focuses on creating authentic synthetic defects and introduces an auto-encoder image reconstruction network with deep feature consistency constraints, as well as a defect separation network with a large receptive field. We conducted experiments on the challenging MVTec anomaly detection dataset and our trained model achieved an AUROC score of 99.70% and an average precision (AP) score of 99.87%. Our method surpasses recently proposed defect detection algorithms, thereby enhancing the accuracy of surface defect detection in industrial products.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Electrical and Control Engineering, Shaanxi University of Science and Technology, Xi'an 710026, China.
- School of Cyber Engineering, Xidian University, Xi'an 710126, China.
Zitieren
APA
Peng, T., Zheng, Y., Zhao, L., & Zheng, E. (2024). Industrial Product Surface Anomaly Detection with Realistic Synthetic Anomalies Based on Defect Map Prediction. Sensors, 24(1), 264. https://doi.org/10.3390/s24010264
Vancouver
Peng T, Zheng Y, Zhao L, Zheng E. Industrial Product Surface Anomaly Detection with Realistic Synthetic Anomalies Based on Defect Map Prediction. Sensors. 2024;24(1):264. doi:10.3390/s24010264
BibTeX
@article{Peng2024,
author = {Peng, Tao and Zheng, Yu and Zhao, Lin and Zheng, Enrang},
title = {Industrial Product Surface Anomaly Detection with Realistic Synthetic Anomalies Based on Defect Map Prediction},
journal = {Sensors},
year = {2024},
volume = {24},
number = {1},
pages = {264},
doi = {10.3390/s24010264}
}
EUVIMED