Anomaly detection in image or latent space of patch-based auto-encoders for industrial image analysis

TL;DR

This paper evaluates various anomaly detection methods using patch-based auto-encoders on industrial images, comparing reconstruction error, latent space support estimation, and image restoration error against state-of-the-art techniques.

Contribution

It provides a comprehensive comparison of three novel anomaly detection approaches based on patch auto-encoders for industrial image analysis.

Findings

Support estimation in latent space improves detection accuracy.

Restoration-based methods outperform simple reconstruction error.

The methods are validated on the MVTecAD industrial database.

Abstract

We study several methods for detecting anomalies in color images, constructed on patch-based auto-encoders. Wecompare the performance of three types of methods based, first, on the error between the original image and its reconstruction,second, on the support estimation of the normal image distribution in the latent space, and third, on the error between the originalimage and a restored version of the reconstructed image. These methods are evaluated on the industrial image database MVTecADand compared to two competitive state-of-the-art methods.