ML Anthology

Bayesian View Class Determination

Anjali Pathak, Octavia I. Camps
CVPR 1993 pp. 407-412
doi:10.1109/CVPR.1993.341098 /cvpr/1993/pathak1993cvpr-bayesian/

Abstract

To recognize objects and to determine their poses in 0 scene we need to find correspondences between the features eztracted from the image and those of the object models. Models are commonly represented by describing a few characteristic views of the object representing groups of views with similar properties. Most feature- based matching schemes assume that 011 the features that are potentially visible in a view will appear with equal probability, and the resulting matching algorithms have to allow for uerrors " without really understanding what they mean. PREMIO M an object recognition system that we3 CAD models of 3D objects and knowledge of rurface reflectance properties, light sources, sensor characteristics, and feature detector algorithms to generate probabilistic models for U given view cluster. The purpose of this poper is to present 0 Bayesian approach to the problem of given an image, how to determine the correct view class it belongs to, using the probabilistic models produced by PREMIO. 1

CVPR Semantic Scholar

Cite

Text

Pathak and Camps. "Bayesian View Class Determination." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1993. doi:10.1109/CVPR.1993.341098

Markdown

[Pathak and Camps. "Bayesian View Class Determination." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1993.](https://mlanthology.org/cvpr/1993/pathak1993cvpr-bayesian/) doi:10.1109/CVPR.1993.341098

BibTeX

@inproceedings{pathak1993cvpr-bayesian,
  title     = {{Bayesian View Class Determination}},
  author    = {Pathak, Anjali and Camps, Octavia I.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1993},
  pages     = {407-412},
  doi       = {10.1109/CVPR.1993.341098},
  url       = {https://mlanthology.org/cvpr/1993/pathak1993cvpr-bayesian/}
}