Measuring the Affine Transform Using Gaussian Filters

Abstract

Image deformations due to relative motion between an observer and an object may be used to infer 3-D structure. Up to first order these deformations can be written in terms of an affine transform. Here, a novel approach is adopted to measuring affine transforms which correctly handles the problem of corresponding deformed patches. The patches are filtered using gaussians and derivatives of gaussians. The problem of finding the affine transform is reduced to that of finding the appropriate deformed filter to use. The method is local and can handle arbitrarily large affine deformations. Experiments demonstrate that this technique can find scale changes and optical flow in situations where other methods fail.

Cite

Text

Manmatha. "Measuring the Affine Transform Using Gaussian Filters." European Conference on Computer Vision, 1994. doi:10.1007/BFB0028346

Markdown

[Manmatha. "Measuring the Affine Transform Using Gaussian Filters." European Conference on Computer Vision, 1994.](https://mlanthology.org/eccv/1994/manmatha1994eccv-measuring/) doi:10.1007/BFB0028346

BibTeX

@inproceedings{manmatha1994eccv-measuring,
  title     = {{Measuring the Affine Transform Using Gaussian Filters}},
  author    = {Manmatha, R.},
  booktitle = {European Conference on Computer Vision},
  year      = {1994},
  pages     = {159-164},
  doi       = {10.1007/BFB0028346},
  url       = {https://mlanthology.org/eccv/1994/manmatha1994eccv-measuring/}
}