Two Images Comparison with Invariance to Illumination Properties
Jean‐Philippe Tarel · 2019
We propose a new way of performing pixel by pixel comparison between two images, taking advantage of interesting invariance properties with respect to illumination conditions and camera settings. Moreover, we show that the proposed operator is relatively robust to strong noise on one of the compared images. The new operator can be used for background subtraction which inherits its invariance properties. The useful properties of the proposed operators are illustrated in the experiments.