ML Anthology

Noise Resistant Projective and Affine Invariants

Isaac Weiss
CVPR 1992 pp. 115-121
doi:10.1109/CVPR.1992.223218 /cvpr/1992/weiss1992cvpr-noise/

Abstract

A method of obtaining local projective and affine invariants that is more robust than existing methods is presented. These shape descriptors are useful for object recognition because they eliminate the search for the unknown viewpoint. Being local, these invariants are much less sensitive to occlusion than the global ones used elsewhere. The basic ideas are (i) using an implicit curve representation without a curve parameter, thus increasing robustness; and (ii) using a canonical coordinate system which is defined by the intrinsic properties of the shape, regardless of any given coordinate system, and is thus invariant. Several configurations are treated: a general curve without any correspondence, and curves with known correspondence of feature points or lines.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

CVPR Semantic Scholar

Cite

Text

Weiss. "Noise Resistant Projective and Affine Invariants." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1992. doi:10.1109/CVPR.1992.223218

Markdown

[Weiss. "Noise Resistant Projective and Affine Invariants." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1992.](https://mlanthology.org/cvpr/1992/weiss1992cvpr-noise/) doi:10.1109/CVPR.1992.223218

BibTeX

@inproceedings{weiss1992cvpr-noise,
  title     = {{Noise Resistant Projective and Affine Invariants}},
  author    = {Weiss, Isaac},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1992},
  pages     = {115-121},
  doi       = {10.1109/CVPR.1992.223218},
  url       = {https://mlanthology.org/cvpr/1992/weiss1992cvpr-noise/}
}