Image Anomalies: a Review and Synthesis of Detection Methods
This work provides a unified framework for image anomaly detection, potentially benefiting researchers and practitioners in computer vision by reconciling diverse methods, though it is incremental in synthesizing existing approaches.
The paper reviews and synthesizes anomaly detection methods in images, classifying them by structural assumptions on normal images and proposing generic algorithms with universal detection thresholds to control false positives, achieving automatic detection on single images.
We review the broad variety of methods that have been proposed for anomaly detection in images. Most methods found in the literature have in mind a particular application. Yet we show that the methods can be classified mainly by the structural assumption they make on the "normal" image. Five different structural assumptions emerge. Our analysis leads us to reformulate the best representative algorithms by attaching to them an a contrario detection that controls the number of false positives and thus derive universal detection thresholds. By combining the most general structural assumptions expressing the background's normality with the best proposed statistical detection tools, we end up proposing generic algorithms that seem to generalize or reconcile most methods. We compare the six best representatives of our proposed classes of algorithms on anomalous images taken from classic papers on the subject, and on a synthetic database. Our conclusion is that it is possible to perform automatic anomaly detection on a single image.