ML Anthology

Indexing via Color Histograms

Michael J. Swain, Dana H. Ballard
ICCV 1990 pp. 390-393
doi:10.1109/ICCV.1990.139558 /iccv/1990/swain1990iccv-indexing/

Abstract

This paper shows color histograms to be stable object representations over change in view, and demonstrates that they can differentiate among a large number of objects. The authors introduce a technique called histogram intersection for efficiently matching model and image histograms. Color can also be used to search for the location of an object. An algorithm called histogram backprojection performs this task efficiently in crowded scenes.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

ICCV Semantic Scholar

Cite

Text

Swain and Ballard. "Indexing via Color Histograms." IEEE/CVF International Conference on Computer Vision, 1990. doi:10.1109/ICCV.1990.139558

Markdown

[Swain and Ballard. "Indexing via Color Histograms." IEEE/CVF International Conference on Computer Vision, 1990.](https://mlanthology.org/iccv/1990/swain1990iccv-indexing/) doi:10.1109/ICCV.1990.139558

BibTeX

@inproceedings{swain1990iccv-indexing,
  title     = {{Indexing via Color Histograms}},
  author    = {Swain, Michael J. and Ballard, Dana H.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1990},
  pages     = {390-393},
  doi       = {10.1109/ICCV.1990.139558},
  url       = {https://mlanthology.org/iccv/1990/swain1990iccv-indexing/}
}