Anomaly detection in image or latent space of patch-based auto-encoders for industrial image analysis
This work addresses anomaly detection for industrial image analysis, but it is incremental as it compares existing method variants without introducing a new paradigm.
The paper tackled anomaly detection in industrial images by comparing three patch-based auto-encoder methods, evaluating them on the MVTecAD database against state-of-the-art approaches.
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.