PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Quality-based Score Normalisation with Device Qualitative Information for Multimodal Biometric Fusion
Norman Poh, Josef Kittler and Thirimahos Bourlai
IEEE Trans. on Systems, Man, Cybernatics Part A : Systems and Humans 2010.

Abstract

As biometric technology is rolled out on a larger scale, it will be a common scenario (known as cross-device matching) to have a template acquired by one biometric device used by another during testing. This requires a biometric system to work with different acquisition devices, an issue known as device interoperability. We further distinguish two sub-problems, depending on whether the device identity is known or unknown. In the latter case, we show that the device information can be probabilistically inferred given quality measures (e.g., image resolution) derived from the raw biometric data. By keeping the template unchanged, cross-device matching can result in significant degradation in performance. We propose to minimise this degradation by using device-specific quality-dependent score normalisation. In the context of fusion, after having normalised each device output independently, these outputs can be combined using the Naive Bayes principal. We have compared, and categorised several state-of-the-art quality-based score normalisation procedures, depending on how the relationship between quality measures and score is modelled, as follows: i) direct modelling, ii) modelling via the cluster index of quality measures, and iii) extending (ii) to further include the device information (devicespecific cluster index). Experimental results carried out on the Biosecure DS2 data set show that the last approach can reduce both false acceptance and false rejection rates simultaneously. Furthermore, the compounded effect of normalising each system individually in multimodal fusion is a significant improvement in performance over the baseline fusion (without using any quality information) when the device information is given.

PDF (This is a preprint version (not typo free)) - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Machine Vision
ID Code:6859
Deposited By:Norman Poh
Deposited On:08 April 2010