Proceedings of the 1998 IEEE International Conference on Computer Vision, Bombay, India We introduce a new distance between two distributions that we call the Earth Mover's D...
The problem of recognizing classes of objects as opposed to special instances requires methods of comparing images that capture the variation within the class while they discrimina...
Abstract We develop a distance metric for clustering and classification algorithms which is invariant to affine transformations and includes priors on the transformation parameters...
We analyze the problem of recovering the shape of a mirror surface. We generalize the results of [1], where the special case of planar and spherical mirror surfaces was considered,...
The knowledge of material specific film grain characteristics can significantly improve the performance of digital film processing algorithms. This paper proposes a rapid and reli...