A New Performance Evaluation Method for Face Identification - Regression Analysis of Misidentification Risk
Abstract
The performance of a face identification system varies with its enrollment size. However, most experiments evaluated the performance of algorithms at only one enrollment size with the rank-1 identification rate. The current practice does not demonstrate the usability of algorithms thoroughly. But the problem is, in order to measure identification performance at different sizes, experimenters have to repeat the evaluation with samples of those sizes, which is almost impossible when they are large. Approaches using the Binomial theorem with match and non-match scores have been proposed to estimate performance at different sizes, but as a separate process from the evaluation itself. This paper presents a new way of evaluating identification algorithms that allows the estimating and comparing of performance at different sizes, using the regression analysis of Misidentification Risk.
Cite
Text
Ho and Watters. "A New Performance Evaluation Method for Face Identification - Regression Analysis of Misidentification Risk." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007. doi:10.1109/CVPR.2007.383276Markdown
[Ho and Watters. "A New Performance Evaluation Method for Face Identification - Regression Analysis of Misidentification Risk." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007.](https://mlanthology.org/cvpr/2007/ho2007cvpr-new/) doi:10.1109/CVPR.2007.383276BibTeX
@inproceedings{ho2007cvpr-new,
title = {{A New Performance Evaluation Method for Face Identification - Regression Analysis of Misidentification Risk}},
author = {Ho, Wai Han and Watters, Paul Andrew},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2007},
doi = {10.1109/CVPR.2007.383276},
url = {https://mlanthology.org/cvpr/2007/ho2007cvpr-new/}
}