Performance Prediction and Validation for Object Recognition

Abstract

This paper addresses the problem of predicting fundamental performance of vote-based object recognition using 2-D point features. It presents a method for predicting a tight lower bound on performance. Unlike previous approaches, the proposed method considers data-distortion factors, namely uncertainty, occlusion, and clutter, in addition to model similarity, simultaneously. The similarity between every pair of model objects is captured by comparing their structures as a function of the relative transformation between them. This information is used along with statistical models of the data-distortion factors to determine an upper bound on the probability of recognition error. This bound is directly used to determine a lower bound on the probability of correct recognition. The validity of the method is experimentally demonstrated using synthetic aperture radar (SAR) data obtained under different depression angles and target configurations.

Cite

Text

Boshra and Bhanu. "Performance Prediction and Validation for Object Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999. doi:10.1109/CVPR.1999.784665

Markdown

[Boshra and Bhanu. "Performance Prediction and Validation for Object Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999.](https://mlanthology.org/cvpr/1999/boshra1999cvpr-performance/) doi:10.1109/CVPR.1999.784665

BibTeX

@inproceedings{boshra1999cvpr-performance,
  title     = {{Performance Prediction and Validation for Object Recognition}},
  author    = {Boshra, Michael and Bhanu, Bir},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1999},
  pages     = {2380-2386},
  doi       = {10.1109/CVPR.1999.784665},
  url       = {https://mlanthology.org/cvpr/1999/boshra1999cvpr-performance/}
}