DocumentCode
2347140
Title
Geometric blur for template matching
Author
Berg, Alexander C. ; Malik, Jitendra
Author_Institution
Comput. Sci. Div., California Univ., Berkeley, CA, USA
Volume
1
fYear
2001
fDate
2001
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.
Keywords
computer vision; face recognition; image matching; transforms; affine distortions; face detection; feature correspondence; geometric blur; point correspondences; template matching; wide baseline stereo correspondence; Computer science; Computer vision; Concrete; Face detection; Image edge detection; Lighting; Object recognition; Robustness; Stereo vision; Uncertainty;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on
ISSN
1063-6919
Print_ISBN
0-7695-1272-0
Type
conf
DOI
10.1109/CVPR.2001.990529
Filename
990529
Link To Document