Rényi divergence as contrast metric for object detection in noisy images

A binary detection task on the presence or absence of an object over a background in noisy images is studied based on a contrast metric taken as the Rényi divergence. The analysis extends, and contains as a special case, previous works realized for the same detection task on the comparison of the Kullback-Leibler divergence and the Bhattacharryya divergence. The extension deals with the influence of the Rényi parameter, the observation scale, the influence of the bit range and the type of noise tested with new noise families of practical interest for imaging.