Handbook of Multibiometrics

By Arun A. Ross, Karthik Nandakumar, Anil K. Jain. 2006

1,209 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

Citations in the corpus

Likelihood Ratio-Based Biometric Score Fusion (2008, background): “Biometric systems based on a single source of information (unibiometric systems) suffer from limitations such as the lack of uniqueness and nonuniversality of the chosen biometric trait, noisy data, and spoof attacks [1].”
An evaluation of indirect attacks and countermeasures in fingerprint verification systems (2011, background): “scores decrease their utility for multi-biometric applications (Ross et al., 2006), which typically rely on fusion techniques of real-valued scores (Fierrez-Aguilar et al., 2005).”
Security evaluation of biometric authentication systems under real spoofing attacks (2012, methodology): “• We normalized all matching scores in [0, 1] using the min-max technique [30], estimating the normalization parameters on the training set.”
Towards anomaly detection for increased security in multibiometric systems: Spoofing-resistant 1-median fusion eliminating outliers (2014, background): “The idea of the proposed fusion scheme at score-level [16] is to consider spoofing attempts in the fusion module.”
Quality-augmented fusion of level-2 and level-3 fingerprint information using DSm theory (2009, neutral): “5 shows that the existing statistical fusion rules such as min–max rule, product rule and sum rule [14,15] increase the veriﬁcation performance by 1–3%.”
Biometric Template Security (2008, background): “A detailed discussion on these types of attacks is presented in Section 2.4.”
Robustness of multi-modal biometric verification systems under realistic spoofing attacks (2011, methodology): “As an alternative to liveness detection, it has been claimed that multi-modal biometric systems are intrinsically more robust against spoofing attacks [11].”
50 years of biometric research: Accomplishments, challenges, and opportunities (2016, positive): “In many cases, a combination or fusion of multiple biometric traits may be required to attain the desired level of performance; such systems are generally referred to as multibiometric systems [80] .”
Personal Authentication Using Finger Knuckle Surface (2009, methodology): “Several feature normalization techniques have been detailed in the literature [18].”
Adversarial Pattern Classification Using Multiple Classifiers and Randomisation (2008, methodology): “Pattern recognition techniques are currently applied to several security applications, like biometric personal authentication, intrusion detection in computer networks and spam filtering [1,2,3,4,5].”
Eyeblink-based Anti-Spoofing in Face Recognition from a Generic Webcamera (2007, background): “Biometrics is an emerging technology that recognizes human identities based upon one or more intrinsic physiological or behavioral characteristics, e.g. faces, fingerprints, irises, voice [1].”
Multiple Classifier Systems for Adversarial Classification Tasks (2009, background): “The second one is an ensemble of classifiers trained on disjoint feature subsets, as in multimodal biometric systems [7, 8].”
Evaluation of multimodal biometric score fusion rules under spoof attacks (2012, methodology): “The FAR predicted by the worst-case assumption of [3, 4, 5] (corresponding to α = 1) is as accurate as the one provided by the considered model, for face spoofing, but is much more inaccurate for fingerprint spoofing, where it overestimates the FAR of about 40 to 50%.”
Multiple Classifier Systems under Attack (2010, methodology): “Another motivation was proposed by several authors: using many classifiers would improve robustness because it would require the adversary to evade all the individual classifiers, or at least more than one of them, to evade the whole system [4, 2, 11].”