Showing papers by "Alexander C. Berg published in 2001"
01 Dec 2001
TL;DR: In this paper, the problem of finding point correspondences in images by way of an approach to template matching that is robust under affine distortions is addressed by applying "geometric blur" to both the template and the image, resulting in a falloff in similarity that is close to linear in the norm of the distortion.
Abstract: We address the problem of finding point correspondences in images by way of an approach to template matching that is robust under affine distortions. This is achieved by applying "geometric blur" to both the template and the image, resulting in a fall-off in similarity that is close to linear in the norm of the distortion between the template and the image. Results in wide baseline stereo correspondence, face detection, and feature correspondence are included.
310 citations