ML Anthology

Histogram-Based Object Recognition Using Shape-from-Shading

Philip L. Worthington, Edwin R. Hancock
CVPR 2000 pp. 1643-1648
doi:10.1109/CVPR.2000.855880 /cvpr/2000/worthington2000cvpr-histogram/

Abstract

This paper presents an experimental study of the problem of object recognition using surface attributes delivered by shape-from-shading. We focus our attention on histogram-based representations. Several surface attributes are considered. These include slant and tilt angles, mean and Gaussian curvature, and, shape-index and curvedness. Our study reveals that recognition rates of 98% are achievable under controlled lighting conditions. When there is significant illumination variation then recognition rates of 80% are achievable.

CVPR Semantic Scholar

Cite

Text

Worthington and Hancock. "Histogram-Based Object Recognition Using Shape-from-Shading." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000. doi:10.1109/CVPR.2000.855880

Markdown

[Worthington and Hancock. "Histogram-Based Object Recognition Using Shape-from-Shading." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000.](https://mlanthology.org/cvpr/2000/worthington2000cvpr-histogram/) doi:10.1109/CVPR.2000.855880

BibTeX

@inproceedings{worthington2000cvpr-histogram,
  title     = {{Histogram-Based Object Recognition Using Shape-from-Shading}},
  author    = {Worthington, Philip L. and Hancock, Edwin R.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2000},
  pages     = {1643-1648},
  doi       = {10.1109/CVPR.2000.855880},
  url       = {https://mlanthology.org/cvpr/2000/worthington2000cvpr-histogram/}
}