ML Anthology

A Transform for Detection of Multiscale Image Structure

Narendra Ahuja
CVPR 1993 pp. 780-781
doi:10.1109/CVPR.1993.341172 /cvpr/1993/ahuja1993cvpr-transform/

Abstract

A new transform is introduced to facilitate integrated edge and region detection in an image at all geometric and photometric scales at which structure is present. The proposed transform allows the structure to emerge from interactions among the pixels. A pixel's interaction with all other pixels is considered instead of testing specific neighborhoods for a specific structure. Computations are performed on pairs of pixels followed by vector integration of the results, rather than scalar, weighted averaging over pixel neighborhoods. For pixels on either side of a region boundary, the transformation yields high affinities, but there is little affinity between pixels across regions.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

PDF CVPR Semantic Scholar

Cite

Text

Ahuja. "A Transform for Detection of Multiscale Image Structure." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1993. doi:10.1109/CVPR.1993.341172

Markdown

[Ahuja. "A Transform for Detection of Multiscale Image Structure." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1993.](https://mlanthology.org/cvpr/1993/ahuja1993cvpr-transform/) doi:10.1109/CVPR.1993.341172

BibTeX

@inproceedings{ahuja1993cvpr-transform,
  title     = {{A Transform for Detection of Multiscale Image Structure}},
  author    = {Ahuja, Narendra},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1993},
  pages     = {780-781},
  doi       = {10.1109/CVPR.1993.341172},
  url       = {https://mlanthology.org/cvpr/1993/ahuja1993cvpr-transform/}
}