ML Anthology

Object Recognition Using Appearance-Based Parts and Relations

Chien-Yuan Huang, Octavia I. Camps, Tapas Kanungo
CVPR 1997 pp. 877-883
doi:10.1109/CVPR.1997.609431 /cvpr/1997/huang1997cvpr-object/

Abstract

The recognition of general three-dimensional objects in cluttered scenes is a challenging problem. In particular, the design of a good representation suitable to model large numbers of generic objects that is also robust to occlusion has been a stumbling block in achieving success. In this paper, we propose a representation using appearance-based parts and relations to overcome these problems. Appearance-based parts and relations are defined in terms of closed regions and the union of these regions, respectively. The regions are segmented using the MDL principle, and their appearance is obtained from collection of images and compactly represented by parametric manifolds in the two eigenspaces spanned by the parts and the relations.

CVPR Semantic Scholar

Cite

Text

Huang et al. "Object Recognition Using Appearance-Based Parts and Relations." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997. doi:10.1109/CVPR.1997.609431

Markdown

[Huang et al. "Object Recognition Using Appearance-Based Parts and Relations." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997.](https://mlanthology.org/cvpr/1997/huang1997cvpr-object/) doi:10.1109/CVPR.1997.609431

BibTeX

@inproceedings{huang1997cvpr-object,
  title     = {{Object Recognition Using Appearance-Based Parts and Relations}},
  author    = {Huang, Chien-Yuan and Camps, Octavia I. and Kanungo, Tapas},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1997},
  pages     = {877-883},
  doi       = {10.1109/CVPR.1997.609431},
  url       = {https://mlanthology.org/cvpr/1997/huang1997cvpr-object/}
}