||In this paper we study set distances which are used in image processing. We propose a generalization of Sum of
minimal distances and show that its special cases include the Hausdorff metric and metric by Symmetric difference.
Chamfer matching distances are also closely related with the presented framework. We also deﬁne the complement set distance of a given set distance. We evaluate the observed distances with respect to applicability to image object registration. We perform comparative evaluation with respect to noise sensitivity, as well as behavior of the distances when images are transformed in controlled ways. We conclude that the family of Generalized sum of minimal distances has many desirable properties for this application.