Frequency perturbation analysis for anomaly detection using Fourier heat map

Yoshikazu Hayashi; Hiroaki Aizawa; Shunsuke Nakatsuka; Kunihito Kato

doi:10.1117/12.2690078

28 July 2023 Frequency perturbation analysis for anomaly detection using Fourier heat map

Yoshikazu Hayashi, Hiroaki Aizawa, Shunsuke Nakatsuka, Kunihito Kato

Proceedings Volume 12749, Sixteenth International Conference on Quality Control by Artificial Vision; 127490B (2023) https://doi.org/10.1117/12.2690078
Event: Sixteenth International Conference on Quality Control by Artificial Vision, 2023, Albi, France

Abstract

Anomaly detection is an essential task within an industry domain, and sophisticated approaches have been proposed. PaDiM has a promising direction, utilizing ImageNet-pretrained convolutional neural networks without expensive training costs. However, the cues and biases utilized by PaDiM, i.e., shape-vs-texture bias in an anomaly detection process, are unclear. To reveal the bias, we proposed to apply frequency analysis to PaDiM. For frequency analysis, we use a Fourier Heat Map that investigates the sensitivity of the anomaly detection model to input noise in the frequency domain. As a result, we found that PaDiM utilizes texture information as a cue for anomaly detection, similar to the classification models. Based on this preliminary experiment, we propose a shape-aware Stylized PaDiM. Our model is a PaDiM that uses pre-trained weights learned on Stylized ImageNet instead of ImageNet. In the experiments, we confirmed that Stylized PaDiM improves the robustness of high-frequency perturbations. Stylized PaDiM also achieved higher performance than PaDiM for anomaly detection in clean images of MVTecAD.

Citation Download Citation

Yoshikazu Hayashi, Hiroaki Aizawa, Shunsuke Nakatsuka, and Kunihito Kato "Frequency perturbation analysis for anomaly detection using Fourier heat map", Proc. SPIE 12749, Sixteenth International Conference on Quality Control by Artificial Vision, 127490B (28 July 2023); https://doi.org/10.1117/12.2690078

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Education and training

Object detection

Matrices

Feature extraction

Fourier spectroscopy

Image restoration

Volume rendering

Show All Keywords

Keywords/Phrases

Search In:

Publication Years