Paper Info
Title
Robust Biometric Score Fusion by Naive Likelihood Ratio via Receiver Operating Characteristics
Abstract
This paper presents a novel method of fusing multiple biometrics on the matching score level. We estimate the likelihood ratios of the fused biometric scores, via individual receiver operating characteristics (ROC) which construct the Naive Bayes classifier. Using a limited number of operation points on the ROC, we are able to realize reliable and robust estimation of the Naive Bayes probability without explicit estimation of the genuine and impostor score distributions. Different from previous work, the method takes into consideration a particular characteristic of the matching score: its quantitative value is already an indication of the sample's likelihood of being genuine. This characteristic is integrated into the proposed method to improve the fusion performance while reducing the inherent algorithmic complexity. We demonstrate by experiments that the proposed method is reliable and robust, suitable for a wide range of matching score distributions in realistic data and public databases.
Year
DOI
Venue
2013
10.1109/TIFS.2012.2231862
IEEE Transactions on Information Forensics and Security
Keywords
Field
DocType
naive bayes classifier,logarithm likelihood ratio,pattern classification,estimation theory,biometric fusion,biometrics (access control),bayes methods,robust estimation,receiver operating characteristics,robust biometric score fusion,roc,naive likelihood ratio,multiple biometrics fusion method,likelihood ratio estimation,sensor fusion,naive bayes probability
Receiver operating characteristic,Biometrics access control,Pattern recognition,Naive Bayes classifier,Computer science,Fusion,Sensor fusion,Artificial intelligence,Estimation theory,Biometrics,Algorithmic complexity
Journal
Volume
Issue
ISSN
8
2
1556-6013
Citations 
PageRank 
References 
10
0.56
16
Authors
2
Name
Order
Citations
PageRank
Qian Tao15914.00
Raymond N. J. Veldhuis243954.16