Image Similarity based on the Discrepancy Norm

In computer vision, or image processing, among the most common tasks are image registration and tracking.
The discrepancy norm is a novel similarity measure. It provides some significantly better properties than the state-of-the-art measures – such as proven monotonicity for shifted signals, or robustness in the face of noise.
In this project we will investigate its properties further and try to adapt it to industrial applications.