Automated Weld Defect Detection in Radiographic Images Using Normalizing Flows
Machines · 09.09.2025 · 13 (9) · 836
DOI: 10.3390/machines13090836 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machines, online erschienen am 09.09.2025. Verfasst von Morteza Mahvelatishamsabadi und 1 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Ulsan (Title: Image anomaly detection for manufacturing processes using Normalizing Flows).
Abstract (Originalsprache)
Anomaly detection is a pressing issue, particularly in industrial images. Detecting weld defects in radiographic images is a challenge due to the small signal-to-noise ratio (SNR) and the limited availability of data. In this paper, we propose an automated weld defect detection method using Normalizing Flows (NFs). We employed various state-of-the-art NF architectures with different feature extractors to detect defects in radiographic images of welds, comprehensively comparing the results with radiographic images of welded steel pipes collected from industrial sites. The results show that the combination of CFlow-AD with a wide residual network-50-2 (WRN-50-2) outperformed the other methods, indicating its effectiveness in anomaly detection.
Förderung
- University of Ulsan (Title: Image anomaly detection for manufacturing processes using Normalizing Flows)
Zitieren
APA
Mahvelatishamsabadi, M., & Lee, S. (2025). Automated Weld Defect Detection in Radiographic Images Using Normalizing Flows. Machines, 13(9), 836. https://doi.org/10.3390/machines13090836
Vancouver
Mahvelatishamsabadi M, Lee S. Automated Weld Defect Detection in Radiographic Images Using Normalizing Flows. Machines. 2025;13(9):836. doi:10.3390/machines13090836
BibTeX
@article{Mahvelatishamsabadi2025,
author = {Mahvelatishamsabadi, Morteza and Lee, Sudong},
title = {Automated Weld Defect Detection in Radiographic Images Using Normalizing Flows},
journal = {Machines},
year = {2025},
volume = {13},
number = {9},
pages = {836},
doi = {10.3390/machines13090836}
}
EUVIMED