You Only Look Once v5 and Multi-Template Matching for Small-Crack Defect Detection on Metal Surfaces
Automation · 07.04.2025 · 6 (2) · 16
DOI: 10.3390/automation6020016 ↗Kurz gefasst
Fachartikel in der Zeitschrift Automation, online erschienen am 07.04.2025. Verfasst von Pallavi Dubey und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: U.S. Department of Energy’s Office of Energy Efficiency and Renewable Energy (EERE), National Science Foundation.
Abstract (Originalsprache)
This paper compares the performance of Deep Learning (DL) and multi-template matching (MTM) models for detecting small defects. DL models extract distinguishing features of objects but require a large dataset of images. In contrast, alternative computer vision techniques like MTM need a relatively small dataset. The lack of large datasets for small metal-surface defects has inhibited the adoption of automation in small-defect detection in remanufacturing settings. This motivated this preliminary study to compare template-based approaches, like MTM, with feature-based approaches, such as DL models, for small-defect detection on an initial laboratory and remanufacturing industry dataset. This study used You Only Look Once v5 (YOLOv5) as the DL model and compared its performance against the MTM model for small-crack detection. The findings of our preliminary investigation are as follows: (i) YOLOv5 demonstrated higher performance than MTM in detecting small cracks; (ii) an extra-large variant of YOLOv5 outperformed a small-size variant; (iii) the size and object variety of the data are crucial in achieving robust pre-trained weights for use in transfer learning; and (iv) enhanced image resolution contributes to precise object detection.
Förderung
- U.S. Department of Energy’s Office of Energy Efficiency and Renewable Energy (EERE)
- National Science Foundation
Zitieren
APA
Dubey, P., Miller, S., Günay, E. E., Jackman, J., Kremer, G. E., & Kremer, P. A. (2025). You Only Look Once v5 and Multi-Template Matching for Small-Crack Defect Detection on Metal Surfaces. Automation, 6(2), 16. https://doi.org/10.3390/automation6020016
Vancouver
Dubey P, Miller S, Günay EE, Jackman J, Kremer GE, Kremer PA. You Only Look Once v5 and Multi-Template Matching for Small-Crack Defect Detection on Metal Surfaces. Automation. 2025;6(2):16. doi:10.3390/automation6020016
BibTeX
@article{Dubey2025,
author = {Dubey, Pallavi and Miller, Seth and Günay, Elif Elçin and Jackman, John and Kremer, Gül E. and Kremer, Paul A.},
title = {You Only Look Once v5 and Multi-Template Matching for Small-Crack Defect Detection on Metal Surfaces},
journal = {Automation},
year = {2025},
volume = {6},
number = {2},
pages = {16},
doi = {10.3390/automation6020016}
}
EUVIMED