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.
Geometric blur for template matching
2001-01-01
1115919 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Geometric Blur and Template Matching
British Library Conference Proceedings | 2001
|Pattern matching using the blur hit-miss transform
British Library Online Contents | 2000
|Real-Time Geometric Motion Blur for a Deforming Polygonal Mesh
British Library Conference Proceedings | 2005
|