[IPOL announce] new article: How to Reduce Anomaly Detection in Images to Anomaly Detection in Noise

[announcements about the IPOL journal]

A new article is available in IPOL: http://www.ipol.im/pub/art/2019/263/

Thibaud Ehret, Axel Davy, Mauricio Delbracio, and Jean-Michel Morel,
How to Reduce Anomaly Detection in Images to Anomaly Detection in Noise,
Image Processing On Line, 9 (2019), pp. 391–412.
https://doi.org/10.5201/ipol.2019.263

Abstract
Anomaly detectors address the difficult problem of detecting 
automatically exceptions in a background image, that can be as diverse 
as a fabric or a mammography. Detection methods have been proposed by 
the thousands because each problem requires a different background 
model. By analyzing the existing approaches, we show that the problem 
can be reduced to detecting anomalies in residual images (extracted from 
the target image) in which noise and anomalies prevail. Hence, the 
general and impossible background modeling problem is replaced by a 
simple noise model, and allows the calculation of rigorous detection 
thresholds. Our approach is therefore unsupervised and works on 
arbitrary images. The residual images can favorably be computed on dense 
features of neural networks. Our detector is powered by the a contrario 
detection theory, which avoids over-detection by fixing detection 
thresholds taking into account the multiple tests.