A Contrario multi-scale anomaly detection method for industrial quality inspection

TL;DR

This paper introduces a multi-scale, unsupervised anomaly detection method using an a contrario framework and statistical analysis of feature maps, effective across various scenarios including industrial quality inspection.

Contribution

It presents a novel multi-scale anomaly detection approach combining statistical analysis with feature maps from deep networks, applicable to diverse applications.

Findings

Achieves state-of-the-art results on public anomaly datasets.

Effectively detects subtle defects in industrial samples.

Works across multiple scales and feature extraction methods.

Abstract

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.