EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

From Anomaly Detection to Defect Classification

Jaromír Klarák iD, Robert Andok, Peter Malík, Ivan Kuric, Mário Ritomský iD, Ivana Klačková iD, Hung-Yin Tsai iD

Sensors · 10.01.2024 · 24 (2) · 429

DOI: 10.3390/s24020429 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 10.01.2024. Verfasst von Jaromír Klarák und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Informatics, Slovak Academy of Sciences, 845 07 Bratislava, Slovakia. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: M-Era.Net, VEGA, APVV.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper proposes a new approach to defect detection system design focused on exact damaged areas demonstrated through visual data containing gear wheel images. The main advantage of the system is the capability to detect a wide range of patterns of defects occurring in datasets. The methodology is built on three processes that combine different approaches from unsupervised and supervised methods. The first step is a search for anomalies, which is performed by defining the correct areas on the controlled object by using the autoencoder approach. As a result, the differences between the original and autoencoder-generated images are obtained. These are divided into clusters using the clustering method (DBSCAN). Based on the clusters, the regions of interest are subsequently defined and classified using the pre-trained Xception network classifier. The main result is a system capable of focusing on exact defect areas using the sequence of unsupervised learning (autoencoder)–unsupervised learning (clustering)–supervised learning (classification) methods (U2S-CNN). The outcome with tested samples was 177 detected regions and 205 occurring damaged areas. There were 108 regions detected correctly, and 69 regions were labeled incorrectly. This paper describes a proof of concept for defect detection by highlighting exact defect areas. It can be thus an alternative to using detectors such as YOLO methods, reconstructors, autoencoders, transformers, etc.

Schlagwörter

Stichwörter der Autor:innen

anomaly detectionautoencoderautomationclusteringdeep learningdefect detectionvisual inspection

Autor:innen und Institutionen

  • Institute of Informatics, Slovak Academy of Sciences, 845 07 Bratislava, Slovakia.
  • Department of Automation and Production Systems, Faculty of Mechanical Engineering, University of Zilina, 010 26 Zilina, Slovakia.
  • Department of Power Mechanical Engineering, National Tsing Hua University, Hsinchu 30013, Taiwan.

ORCID-Profile: Jaromír Klarák, Mário Ritomský, Ivana Klačková, Hung-Yin Tsai

Förderung

  • M-Era.Net
  • VEGA
  • APVV

Zitieren

APA

Klarák, J., Andok, R., Malík, P., Kuric, I., Ritomský, M., Klačková, I., & Tsai, H. Y. (2024). From Anomaly Detection to Defect Classification. Sensors, 24(2), 429. https://doi.org/10.3390/s24020429

Vancouver

Klarák J, Andok R, Malík P, Kuric I, Ritomský M, Klačková I, et al. From Anomaly Detection to Defect Classification. Sensors. 2024;24(2):429. doi:10.3390/s24020429

BibTeX
@article{Klark2024,
  author = {Klarák, Jaromír and Andok, Robert and Malík, Peter and Kuric, Ivan and Ritomský, Mário and Klačková, Ivana and Tsai, Hung-Yin},
  title = {From Anomaly Detection to Defect Classification},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {2},
  pages = {429},
  doi = {10.3390/s24020429}
}
Kostenlos starten →