Sciweavers

Share
CVPR
2001
IEEE

Geometric Blur for Template Matching

10 years 11 days ago
Geometric Blur for Template Matching
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.
Alexander C. Berg, Jitendra Malik
Added 12 Oct 2009
Updated 29 Oct 2009
Type Conference
Year 2001
Where CVPR
Authors Alexander C. Berg, Jitendra Malik
Comments (0)
books