ML Anthology

Using Illumination Invariant Descriptors for Recognition

Glenn Healey, David Slater
CVPR 1994 pp. 355-360
doi:10.1109/CVPR.1994.323851 /cvpr/1994/healey1994cvpr-using/

Abstract

Color pixel distributions provide a useful cue for object recognition. Recently, for example, a technique called color indexing due to M. Swain and D. Ballard (1991) used color histograms for the efficient recognition of objects from a large database in the presence of changes in scene geometry and occlusion. The effectiveness of this and other approaches that match color distributions, however, depends on the approximate constancy of the scene illumination. In this paper, we develop color histogram descriptors that are invariant to changes in the intensity and spectral distribution of the illumination. We present a set of experiments that demonstrate the effectiveness of these descriptors for object recognition in the presence of changes in illuminant spectral power distribution.< <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

Healey and Slater. "Using Illumination Invariant Descriptors for Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1994. doi:10.1109/CVPR.1994.323851

Markdown

[Healey and Slater. "Using Illumination Invariant Descriptors for Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1994.](https://mlanthology.org/cvpr/1994/healey1994cvpr-using/) doi:10.1109/CVPR.1994.323851

BibTeX

@inproceedings{healey1994cvpr-using,
  title     = {{Using Illumination Invariant Descriptors for Recognition}},
  author    = {Healey, Glenn and Slater, David},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1994},
  pages     = {355-360},
  doi       = {10.1109/CVPR.1994.323851},
  url       = {https://mlanthology.org/cvpr/1994/healey1994cvpr-using/}
}