ML Anthology

Geometric Blur for Template Matching

Alexander C. Berg, Jitendra Malik
CVPR 2001 pp. I:607-614
doi:10.1109/CVPR.2001.990529 /cvpr/2001/berg2001cvpr-geometric/

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.

CVPR Semantic Scholar

Cite

Text

Berg and Malik. "Geometric Blur for Template Matching." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001. doi:10.1109/CVPR.2001.990529

Markdown

[Berg and Malik. "Geometric Blur for Template Matching." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001.](https://mlanthology.org/cvpr/2001/berg2001cvpr-geometric/) doi:10.1109/CVPR.2001.990529

BibTeX

@inproceedings{berg2001cvpr-geometric,
  title     = {{Geometric Blur for Template Matching}},
  author    = {Berg, Alexander C. and Malik, Jitendra},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2001},
  pages     = {I:607-614},
  doi       = {10.1109/CVPR.2001.990529},
  url       = {https://mlanthology.org/cvpr/2001/berg2001cvpr-geometric/}
}