Deformable Kernels for Early Vision

Perona, Pietro

doi:10.1109/CVPR.1991.139691

Deformable Kernels for Early Vision

Pietro Perona

CVPR 1991 pp. 222-227

doi:10.1109/CVPR.1991.139691 /cvpr/1991/perona1991cvpr-deformable/

Abstract

A technique is presented that allows (1) computing the best approximation of a given family using linear combinations of a small number of basis functions; and (2) describing all finite-dimensional families, i.e. the families of filters for which a finite-dimensional representation is possible with no error. The technique is general and can be applied to generating filters in arbitrary dimensions. Experimental results that demonstrate the applicability of the technique to generating multi-orientation multiscale 2-D edge-detection kernels are presented. The implementation issues are also discussed.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>

PDF CVPR Semantic Scholar

Cite

Text

Perona. "Deformable Kernels for Early Vision." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991. doi:10.1109/CVPR.1991.139691

Markdown

[Perona. "Deformable Kernels for Early Vision." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991.](https://mlanthology.org/cvpr/1991/perona1991cvpr-deformable/) doi:10.1109/CVPR.1991.139691

BibTeX

@inproceedings{perona1991cvpr-deformable,
  title     = {{Deformable Kernels for Early Vision}},
  author    = {Perona, Pietro},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1991},
  pages     = {222-227},
  doi       = {10.1109/CVPR.1991.139691},
  url       = {https://mlanthology.org/cvpr/1991/perona1991cvpr-deformable/}
}