A Multi-Scale A Contrario method for Unsupervised Image Anomaly Detection

10/05/2021
by   Matias Tailanian, et al.
16

Anomalies can be defined as any non-random structure which deviates from normality. Anomaly detection methods reported in the literature are numerous and diverse, as what is considered anomalous usually varies depending on particular scenarios and applications. In this work we propose an a contrario framework to detect anomalies in images applying statistical analysis to feature maps obtained via convolutions. We evaluate filters learned from the image under analysis via patch PCA, Gabor filters and the feature maps obtained from a pre-trained deep neural network (Resnet). The proposed method is multi-scale and fully unsupervised and is able to detect anomalies in a wide variety of scenarios. While the end goal of this work is the detection of subtle defects in leather samples for the automotive industry, we show that the same algorithm achieves state of the art results in public anomalies datasets.

READ FULL TEXT

page 1

page 4

page 7

research
04/09/2021

MLF-SC: Incorporating multi-layer features to sparse coding for anomaly detection

Anomalies in images occur in various scales from a small hole on a carpe...
research
08/29/2023

MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detection

Unsupervised anomaly detection (UAD) attracts a lot of research interest...
research
03/12/2022

LesionPaste: One-Shot Anomaly Detection for Medical Images

Due to the high cost of manually annotating medical images, especially f...
research
12/13/2020

DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation

Automatic detecting anomalous regions in images of objects or textures w...
research
12/12/2022

Multi-scale Feature Imitation for Unsupervised Anomaly Localization

The unsupervised anomaly localization task faces the challenge of missin...
research
09/30/2022

Learning Second Order Local Anomaly for General Face Forgery Detection

In this work, we propose a novel method to improve the generalization ab...
research
11/01/2022

Siamese Transition Masked Autoencoders as Uniform Unsupervised Visual Anomaly Detector

Unsupervised visual anomaly detection conveys practical significance in ...

Please sign up or login with your details

Forgot password? Click here to reset