@guillem.palou

Geometric blur for template matching

, and . Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conf. on, 1, page I----607----I----614 vol.1. (2001)
DOI: 10.1109/CVPR.2001.990529

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.

Links and resources

Tags

community