Computer Vision, IEEE International Conference on (2011)
Nov. 6, 2011 to Nov. 13, 2011
Zhengwu Zhang , Florida State University, USA
Eric Klassen , Florida State University, USA
Anuj Srivastava , Florida State University, USA
Pavan Turaga , University of Maryland, USA
Rama Chellappa , University of Maryland, USA
We propose a novel Riemannian framework for comparing signals and images in a manner that is invariant to their levels of blur. This framework uses a log-Fourier representation of signals/images in which the set of all possible Gaussian blurs of a signal, i.e. its orbits under semigroup action of Gaussian blur functions, is a straight line. Using a set of Riemannian metrics under which the group actions are by isometries, the orbits are compared via distances between orbits. We demonstrate this framework using a number of experimental results involving 1D signals and 2D images.
E. Klassen, Zhengwu Zhang, A. Srivastava, R. Chellappa and P. Turaga, "Blurring-invariant Riemannian metrics for comparing signals and images," 2011 IEEE International Conference on Computer Vision (ICCV 2011)(ICCV), Barcelona, 2011, pp. 1770-1775.