ML Anthology

Directional Histogram Model for Three-Dimensional Shape Similarity

Xinguo Liu, Robin Sun, Sing Bing Kang, Heung-Yeung Shum
CVPR 2003 pp. 813-820
doi:10.1109/CVPR.2003.1211436 /cvpr/2003/liu2003cvpr-directional/

Abstract

In this paper, we propose a novel shape representation we call directional histogram model (DHM). It captures the shape variation of an object and is invariant to scaling and rigid transforms. The DHM is computed by first extracting a directional distribution of thickness histogram signatures, which are translation invariant. We show how the extraction of the thickness histogram distribution can be accelerated using conventional graphics hardware. Orientation invariance is achieved by computing the spherical harmonic transform of this distribution. Extensive experiments show that the DHM is capable of high discrimination power and is robust to noise.

PDF CVPR Semantic Scholar

Cite

Text

Liu et al. "Directional Histogram Model for Three-Dimensional Shape Similarity." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003. doi:10.1109/CVPR.2003.1211436

Markdown

[Liu et al. "Directional Histogram Model for Three-Dimensional Shape Similarity." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003.](https://mlanthology.org/cvpr/2003/liu2003cvpr-directional/) doi:10.1109/CVPR.2003.1211436

BibTeX

@inproceedings{liu2003cvpr-directional,
  title     = {{Directional Histogram Model for Three-Dimensional Shape Similarity}},
  author    = {Liu, Xinguo and Sun, Robin and Kang, Sing Bing and Shum, Heung-Yeung},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2003},
  pages     = {813-820},
  doi       = {10.1109/CVPR.2003.1211436},
  url       = {https://mlanthology.org/cvpr/2003/liu2003cvpr-directional/}
}