Gaussian Error Models for Object Recognition
Abstract
The probability of false positives and negatives is derived as a function of the number of model features, image features, and occlusion, under the assumption of 2D Gaussian noise and a particular method of evidence accumulation. No assumptions are made about prior distributions on the model space, nor is even the presence of the model assumed. The results are presented in the form of ROC (receiver-operating characteristic) curves, from which several results can be extracted. They demonstrate that the 2D Gaussian error model has better performance than that of the bounded uniform model for the same level of occlusion and clutter. They also directly indicate the optimal performance that can be achieved for a given clutter and occlusion rate and how to choose the thresholds to achieve the desired rates. These ROC curves are verified in the domain of simulated images.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
Cite
Text
Sarachik and Grimson. "Gaussian Error Models for Object Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1993. doi:10.1109/CVPR.1993.341099Markdown
[Sarachik and Grimson. "Gaussian Error Models for Object Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1993.](https://mlanthology.org/cvpr/1993/sarachik1993cvpr-gaussian/) doi:10.1109/CVPR.1993.341099BibTeX
@inproceedings{sarachik1993cvpr-gaussian,
title = {{Gaussian Error Models for Object Recognition}},
author = {Sarachik, Karen Beth and Grimson, W. Eric L.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {1993},
pages = {400-406},
doi = {10.1109/CVPR.1993.341099},
url = {https://mlanthology.org/cvpr/1993/sarachik1993cvpr-gaussian/}
}