Biometric fusion: does modeling correlation really matter?

Authors:
Karthik Nandakumar;Arun Ross;Anil K. Jain
Affiliations:
Institute for Infocomm Research, A*STAR, Fusionopolis, Singapore;Department of Computer Science & Electrical Engineering, West Virginia University, Morgantown, WV;Department of Computer Science and Engineering, Michigan State University, East Lansing, MI
Venue:
BTAS'09 Proceedings of the 3rd IEEE international conference on Biometrics: Theory, applications and systems
Year:
2009

Citing 8
Cited 1

Unsupervised Learning of Finite Mixture Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
FVC2002: Second Fingerprint Verification Competition

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3
Handbook of Multibiometrics (International Series on Biometrics)

Handbook of Multibiometrics (International Series on Biometrics)
Interpreting Kullback-Leibler divergence with the Neyman-Pearson lemma

Journal of Multivariate Analysis - Special issue dedicated to Professor Yasunori Fujikoshi
Database, protocols and tools for evaluating score-level fusion algorithms in biometric authentication

Pattern Recognition
Likelihood Ratio-Based Biometric Score Fusion

IEEE Transactions on Pattern Analysis and Machine Intelligence
A parametric copula based framework for multimodal signal processing

ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
A principled approach to score level fusion in multimodal biometric systems

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

Sequential fusion using correlated decisions for controlled verification errors

CAIP'11 Proceedings of the 14th international conference on Computer analysis of images and patterns - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

Sources of information in a multibiometric system are often assumed to be statistically independent in order to simplify the design of the fusion algorithm. However, the independence assumption may not be always valid. In this paper, we analyze whether modeling the dependence between match scores in a multibiometric system has any effect on the fusion performance. Our analysis is based on the likelihood ratio (LR) based fusion framework, which guarantees optimal performance if the match score densities are known. We show that the assumption of independence between matchers has a significant negative impact on the performance of the LR fusion scheme only when (i) the dependence characteristics among genuine match scores is different from that of the impostor scores and (ii) the individual matchers are not very accurate.