Limitations of anomaly detection: beyond which size defects can be reliably recognized

Jan Lehr; Martin Pape; Jan Philipps; Felix Scholler; Jörg Krüger

doi:10.1117/12.3023615

3 April 2024 Limitations of anomaly detection: beyond which size defects can be reliably recognized

Jan Lehr, Martin Pape, Jan Philipps, Felix Scholler, Jörg Krüger

Proceedings Volume 13072, Sixteenth International Conference on Machine Vision (ICMV 2023); 130720H (2024) https://doi.org/10.1117/12.3023615
Event: Sixteenth International Conference on Machine Vision (ICMV 2023), 2023, Yerevan, Armenia

Abstract

Anomaly detection is one of the most popular fields for computer vision in industrial applications. The idea of training machine learning only on defect-free objects saves enormous amounts of integration effort. The state of the art shows that current methods on public data sets (e.g. MVTec AD data set) have already solved the problem with AUROC segmentations scores of more than 99%. But how accurate are these methods really? In this paper, one current method from the field of supervised learning and anomaly detection is evaluated on two problems. Each problem contains a defect pattern that grows in 11 steps. This work shows that the defect is already reliably detected from a relative size of 0.03% of the pixels in the image.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Jan Lehr, Martin Pape, Jan Philipps, Felix Scholler, and Jörg Krüger "Limitations of anomaly detection: beyond which size defects can be reliably recognized", Proc. SPIE 13072, Sixteenth International Conference on Machine Vision (ICMV 2023), 130720H (3 April 2024); https://doi.org/10.1117/12.3023615

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available