The Earth Mover's distance was first introduced as a purely empirical way to measure texture and color similarities. We show that it has a rigorous probabilistic interpretati...
Correlation is a very effective way to align intensity images. We extend the correlation technique to point set registration using a method we call kernel correlation. Kernel corre...
Abstract. Two new techniques based on nonparametric estimation of probability densities are introduced which improve on the performance of equivalent robust methods currently emplo...
Abstract. Regularization o ers a powerful framework for signal reconstruction by enforcing weak constraints through the use of stabilizers. Stabilizers are functionals measuring th...
Abstract. We propose a new approach to the correspondence problem that makes use of non-parametric local transforms as the basis for correlation. Non-parametric local transforms re...