A radial cumulative similarity transform for robust image correspondence

T. Darrell
Interval Research Corp.
1801C Page Mill Road
Palo Alto CA 94304
[ Click here for a compressed PostScript version of this report ]
[ Click here for a PDF version of this report ]
[ Click here for HTML version of related Powerpoint slides ]



We develop a local image-correspondence algorithm which performs well near occluding boundaries. Unlike traditional robust methods, our method can find correspondences when the only contrast present is the occluding boundary itself and when the sign of contrast along the boundary is possibly reversed. We define a new image transform which characterizes local image homogeneity, defined as an attribute value in a central region and a function describing the surrounding local similarity structure. In this paper we use radial similarity functions and color attributes; within each window we compute the central color and an image with the cumulative probability that color is unchanged along a ray from the center to a given point in the window. This representation is insensitive to structure outside an occluding boundary, but can model the boundary itself. We show comparative results tracking finger, mouth, and eye features.

A shorter version of this paper appears in Proceedings of the Conference on Computer Vistion and Pattern Recognition, pp. 656-662, Santa Barbera, June 1998

©1998 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in orther works must be obtained from the IEEE.

Trevor Darrell