ML Anthology

Finding Glass

Kenton McHenry, Jean Ponce, David A. Forsyth
CVPR 2005 pp. 973-979
doi:10.1109/CVPR.2005.161 /cvpr/2005/mchenry2005cvpr-finding/

Abstract

This paper addresses the problem of finding glass objects in images. Visual cues obtained by combining the systematic distortions in background texture occurring at the boundaries of transparent objects with the strong highlights typical of glass surfaces are used to train a hierarchy of classifiers, identify glass edges, and find consistent support regions for these edges. Qualitative and quantitative experiments involving a number of different classifiers and real images are presented.

CVPR Semantic Scholar

Cite

Text

McHenry et al. "Finding Glass." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005. doi:10.1109/CVPR.2005.161

Markdown

[McHenry et al. "Finding Glass." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005.](https://mlanthology.org/cvpr/2005/mchenry2005cvpr-finding/) doi:10.1109/CVPR.2005.161

BibTeX

@inproceedings{mchenry2005cvpr-finding,
  title     = {{Finding Glass}},
  author    = {McHenry, Kenton and Ponce, Jean and Forsyth, David A.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2005},
  pages     = {973-979},
  doi       = {10.1109/CVPR.2005.161},
  url       = {https://mlanthology.org/cvpr/2005/mchenry2005cvpr-finding/}
}