Deep Autoencoders for Anomaly Detection in Textured Images using CW-SSIM

TL;DR

This paper introduces a deep autoencoder trained with CW-SSIM loss for improved anomaly detection in textured images, outperforming traditional methods with simpler models.

Contribution

It demonstrates that using CW-SSIM as a loss function enhances anomaly detection performance in textured images with a simpler autoencoder architecture.

Findings

CW-SSIM loss improves detection accuracy

Simple autoencoder matches or exceeds complex models

Effective on standard anomaly detection benchmarks

Abstract

Detecting anomalous regions in images is a frequently encountered problem in industrial monitoring. A relevant example is the analysis of tissues and other products that in normal conditions conform to a specific texture, while defects introduce changes in the normal pattern. We address the anomaly detection problem by training a deep autoencoder, and we show that adopting a loss function based on Complex Wavelet Structural Similarity (CW-SSIM) yields superior detection performance on this type of images compared to traditional autoencoder loss functions. Our experiments on well-known anomaly detection benchmarks show that a simple model trained with this loss function can achieve comparable or superior performance to state-of-the-art methods leveraging deeper, larger and more computationally demanding neural networks.