Improving Industrial Quality Control: A Transfer Learning Approach to Surface Defect Detection
Sensors · 17.01.2025 · 25 (2) · 527
DOI: 10.3390/s25020527 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 17.01.2025. Verfasst von Ângela Semitela und 4 weiteren Autor:innen. Beteiligte Einrichtung: Centre of Mechanical Technology and Automation (TEMA), Department of Mechanical Engineering, University of Aveiro, 3810-193 Aveiro, Portugal. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: PRR - Plano de Recuperação e Resiliência under the Next Generation EU from the European Union, Fundação para a Ciência e Tecnologia, PRR—Plano de Recuperação e Resiliência under the Next Generation EU from the European Union.
Abstract (Originalsprache)
To automate the quality control of painted surfaces of heating devices, an automatic defect detection and classification system was developed by combining deflectometry and bright light-based illumination on the image acquisition, deep learning models for the classification of non-defective (OK) and defective (NOK) surfaces that fused dual-modal information at the decision level, and an online network for information dispatching and visualization. Three decision-making algorithms were tested for implementation: a new model built and trained from scratch and transfer learning of pre-trained networks (ResNet-50 and Inception V3). The results revealed that the two illumination modes employed widened the type of defects that could be identified with this system, while maintaining its lower computational complexity by performing multi-modal fusion at the decision level. Furthermore, the pre-trained networks achieved higher accuracies on defect classification compared to the self-built network, with ResNet-50 displaying higher accuracy. The inspection system consistently obtained fast and accurate surface classifications because it imposed OK classification on models trained with images from both illumination modes. The obtained surface information was then successfully sent to a server to be forwarded to a graphical user interface for visualization. The developed system showed considerable robustness, demonstrating its potential as an efficient tool for industrial quality control.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Centre of Mechanical Technology and Automation (TEMA), Department of Mechanical Engineering, University of Aveiro, 3810-193 Aveiro, Portugal.
- Intelligent Systems Associate Laboratory (LASI), 4800-058 Guimarães, Portugal.
- Institute of Electronics and Informatics Engineering of Aveiro (IEETA), Department of Electronics, Telecommunications and Informatics, University of Aveiro, 3810-193 Aveiro, Portugal.
ORCID-Profile: Ângela Semitela, António Completo, José P Santos
Förderung
- PRR - Plano de Recuperação e Resiliência under the Next Generation EU from the European Union
- Fundação para a Ciência e Tecnologia
- PRR—Plano de Recuperação e Resiliência under the Next Generation EU from the European Union
- Fundação para a Ciência e Tecnologia I.P. (FCT, IP)
Zitieren
APA
Semitela, Â., Pereira, M., Completo, A., Lau, N., & Santos, J. P. (2025). Improving Industrial Quality Control: A Transfer Learning Approach to Surface Defect Detection. Sensors, 25(2), 527. https://doi.org/10.3390/s25020527
Vancouver
Semitela Â, Pereira M, Completo A, Lau N, Santos JP. Improving Industrial Quality Control: A Transfer Learning Approach to Surface Defect Detection. Sensors. 2025;25(2):527. doi:10.3390/s25020527
BibTeX
@article{Semitela2025,
author = {Semitela, Ângela and Pereira, Miguel and Completo, António and Lau, Nuno and Santos, José P},
title = {Improving Industrial Quality Control: A Transfer Learning Approach to Surface Defect Detection},
journal = {Sensors},
year = {2025},
volume = {25},
number = {2},
pages = {527},
doi = {10.3390/s25020527}
}
EUVIMED