This chapter contributes towards advancing finger vein template protection research by presenting the first analysis on the suitability of the BioHashing template protection scheme for finger vein verification systems, in terms of the effect on the system's recognition performance. Our results show the best performance when BioHashing is applied to finger vein patterns extracted using the Wide Line Detector (WLD) and Repeated Line Tracking (RLT) feature extractors, and the worst performance when the Maximum Curvature (MC) extractor is used. The low recognition performance in the Stolen Token scenario is shown to be improvable by increasing the BioHash length; however, we demonstrate that the BioHash length is constrained in practice by the amount of memory required for the projection matrix. So, WLD finger vein patterns are found to be the most promising for BioHashing purposes due to their relatively small feature vector size, which allows us to generate larger BioHashes than is possible for RLT or MC feature vectors. In addition, we also provide an open-source implementation of a BioHash-protected finger vein verification system based on the WLD, RLT and MC extractors, so that other researchers can verify our findings and build upon our work.

This paper makes a first attempt at quantifying the entropy of fingervein patterns that have been extracted using three different state-of-the-art feature extractors, on two publicly-available fingervein databases. We show that the resulting entropy is dependent upon both the feature extractor and database, implying that a universal estimate of fingervein entropy would be misleading. We also discuss how our entropy results can be applied towards more meaningful evaluations of the security and privacy of fingervein template protection schemes. Our open-source implementation of the entropy estimation on a publicly-available fingervein recognition system will help the research community to both validate our findings and build upon our work.

The fuzzy vault construction is one of the most widely adopted approaches for the protection of fingerprint data. The popularity of this scheme stems from its ability to deal with unordered sets of fingerprint features, as well as its tolerance to missing or spurious feature elements across multiple acquisitions of the same fingerprint. While a considerable number of fingerprint-based fuzzy vault implementations have been reported in the literature, a review of these schemes does not yet exist, to the best of the authors' knowledge. This paper, therefore, dissects existing fingerprint fuzzy vault schemes and provides a comprehensive discussion of what fingerprint features have been used, and how the locking and unlocking processes have been adapted to suit the nature of the fingerprint features employed.

This chapter makes the first attempt to quantify the amount of discriminatory information in finger vein biometric characteristics in terms of Relative Entropy (RE) calculated on genuine and impostor comparison scores using a Nearest Neighbour (NN) estimator. Our findings indicate that the RE is system-specific, meaning that it would be misleading to claim a universal finger vein RE estimate. We show, however, that the RE can be used to rank finger vein recognition systems (tested on the same database using the same experimental protocol) in terms of their expected recognition accuracy, and that this ranking is equivalent to that achieved using the EER. This implies that the RE estimator is a reliable indicator of the amount of discriminatory information in a finger vein recognition system. We also propose a Normalised Relative Entropy (NRE) metric to help us better understand the significance of the RE values, as well as to enable a fair benchmark of different biometric systems (tested on different databases and potentially using different experimental protocols) in terms of their RE. We discuss how the proposed NRE metric can be used as a complement to the EER in benchmarking the discriminative capabilities of different biometric systems, and we consider two potential issues that must be taken into account when calculating the RE and NRE in practice.

A significant challenge in the development of automated fingerprint recognition algorithms is dealing with missing minutiae. While it is generally assumed that some minutiae will always be missing between multiple samples of the same fingerprint, this assumption has never been empirically evaluated. An important factor influencing minutiae persistence in civilian fingerprint recognition applications is the consistency with which a user places their finger on the fingerprint scanner during fingerprint image acquisition. This paper investigates the probability of a reference minutia repeating in another sample of the same person's fingerprint, when that probability depends on user consistency alone. The investigation targets cooperative users in a civilian fingerprint recognition application. To simulate this scenario, a database of 800 fingerprint samples from 100 participants was collected. Analysis of the database showed that the median probability of a reference minutia repeating in another sample of the same fingerprint is 0.95 with an interquartile range of 0.04. Combining multiple samples of the same fingerprint to filter out only the most reliable reference minutiae was shown to improve this probability. A complementary study demonstrated that automatic feature extractors and matchers may lower minutiae repeatability, but that user consistency is nevertheless the most influential factor. Bifurcation Termination 76