Performance Generalization in Biometric Authentication Using Joint User-Specific and Sample Bootstraps

Authors:
Norman Poh;Alvin Martin;Samy Bengio
Affiliations:
IEEE;-;IEEE
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2007

Citing 6
Cited 3

Unsupervised Learning of Finite Mixture Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Error analysis of pattern recognition systems: the subsets bootstrap

Computer Vision and Image Understanding
Biometric Systems: Technology, Design and Performance Evaluation

Biometric Systems: Technology, Design and Performance Evaluation
ROC confidence bands: an empirical evaluation

ICML '05 Proceedings of the 22nd international conference on Machine learning
Database, protocols and tools for evaluating score-level fusion algorithms in biometric authentication

Pattern Recognition
Calculation of a composite DET curve

AVBPA'05 Proceedings of the 5th international conference on Audio- and Video-Based Biometric Person Authentication

A parametric correlation framework for the statistical evaluation and estimation of biometric-based classification performance in a single environment

IEEE Transactions on Information Forensics and Security
Curvewise DET confidence regions and pointwise EER confidence intervals using radial sweep methodology

ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics
Predicting biometric authentication system performance across different application conditions: a bootstrap enhanced parametric approach

ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics

Quantified Score

Hi-index	0.14

Visualization

Abstract

Biometric authentication performance is often depicted by a detection error trade-off (DET) curve. We show that this curve is dependent on the choice of samples available, the demographic composition and the number of users specific to a database. We propose a two-step bootstrap procedure to take into account the three mentioned sources of variability. This is an extension to the Bolle et al.'s bootstrap subset technique. Preliminary experiments on the NIST2005 and XM2VTS benchmark databases are encouraging, e.g., the average result across all 24 systems evaluated on NIST2005 indicates that one can predict, with more than 75 percent of DET coverage, an unseen DET curve with eight times more users. Furthermore, our finding suggests that with more data available, the confidence intervals become smaller and, hence, more useful.