Handbook of Vascular Biometrics pp 507-525 | Cite as

# Towards Measuring the Amount of Discriminatory Information in Finger Vein Biometric Characteristics Using a Relative Entropy Estimator

## Abstract

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.

## Keywords

Finger veins Relative entropy Nearest neighbour estimator Biometric template protection Security Privacy Discriminatory information Kullback–Leibler divergence VERA UTFVP Wide Line Detector Repeated Line Tracking Maximum Curvature## 17.1 Introduction

There is no doubt that biometrics are fast becoming ubiquitous in response to a growing need for more robust identity assurance. A negative consequence of this increasing reliance on biometrics is the looming threat of serious privacy and security concerns in the event that the growing biometric databases are breached.^{1} Fortunately, the past decade has seen notable efforts in advancing the field of biometric template protection, which is dedicated to protecting the biometric data that is collected and used for recognition purposes, thereby safeguarding the privacy of the data subjects and preventing “spoofing” attacks using stolen biometric templates. Unfortunately, we are still lacking solid methods for evaluating the effectiveness of the proposed solutions. An important missing ingredient is a measure of the amount of discriminatory information in a biometric system.

A few approaches, for example, [1, 2, 3], have focused on estimating the “individuality” (or discrimination capability) of biometric templates in terms of the inter-class variation alone (i.e. the False Match Rate or False Accept Rate). Along the same lines, the best-known attempt to measure the amount of information in a biometric system is probably the approach proposed by Daugman [4]. This method computes the Hamming distance between every pair of non-mated IrisCodes, and the resulting distance distribution is then fitted to a binomial distribution. The number of degrees of freedom of the representative binomial distribution approximates the number of independent bits in each binary IrisCode, which in turn provides an estimate for the discrimination entropy of the underlying biometric characteristic. This approach was adopted to measure the entropy of finger vein patterns in [5]. However, as explained in [5], while this method of measuring entropy is correct from the source coding point of view, the issue with calculating the entropy in this way is that it only provides a reasonable estimate of the amount of biometric information if there is no variation between multiple samples captured from the same biometric instance. Since this intra-class variation is unlikely to be zero in practice, the discrimination entropy would probably overestimate the amount of available biometric information [6, 7].

In an attempt to extend the idea of using entropy as a measure of biometric information while more practically incorporating both inter- and intra-class variation, several authors have adopted the *relative entropy* approach. Adler et al. [8] defined the term “biometric information” as *the decrease in uncertainty about the identity of a person due to a set of biometric measurements*. They proposed estimating the biometric information via the *relative entropy* or *Kullback–Leibler (KL) Divergence* between the intra-class and inter-class biometric feature distributions. Takahashi and Murakami [6] adopted a similar approach to [8], except that they used *comparison score* distributions instead of *feature* distributions, since this ensures that the whole recognition pipeline is considered when estimating the amount of discriminative biometric information in the system. Around the same time, Sutcu et al. [9] adopted the same method as that employed in [6], with an important difference: they used a Nearest Neighbour (NN) estimator for the KL divergence, thereby removing the need to establish models for the comparison score distributions prior to computing the relative entropy.

This paper adopts the approach proposed in [9] to estimate the amount of discriminatory information in finger vein biometrics. We show that the Relative Entropy (RE) metric is equivalent to the Equal Error Rate (EER) in terms of enabling us to rank finger vein biometric systems according to their expected recognition accuracy. This suggests that the RE metric can provide a reliable estimation of the amount of discriminatory information in finger vein recognition systems. We additionally propose a Normalised Relative Entropy (NRE) metric to help us gain a more intuitive understanding of the significance of RE values and to allow us to fairly benchmark the REs of different biometric systems. The new metric can be used in conjunction with the EER to determine the best-performing biometric system.

The remainder of this chapter is structured as follows. Section 17.2 explains the adopted RE metric in more detail. Section 17.3 presents our results for the RE of finger vein patterns and shows how this metric can be used to rank finger vein recognition systems in comparison with the EER. Section 17.4 proposes the new NRE metric and presents NRE results on various finger vein recognition systems. Section 17.5 discusses how the NRE could be a useful complement to the EER in benchmarking the discrimination capabilities of different biometric systems, and we also present two issues that must be considered when calculating the RE and NRE in practice. Section 17.6 concludes this chapter and proposes a primary direction for future work.

## 17.2 Measuring Biometric Information via Relative Entropy

*G*(

*x*) represents the probability distribution of

*genuine*(mated) comparison scores in a biometric recognition system, and

*I*(

*x*) represents the probability distribution of

*impostor*(non-mated) comparison scores. The RE between these two distributions is then defined in terms of the KL divergence as follows:

*D*(

*G*||

*I*) tells us the number of extra bits that we would need to encode samples from

*G*when using a code based on

*I*, compared to simply using a code based on

*G*itself. Relating this to our biometric system, we can think of

*D*(

*G*||

*I*) as providing some indication of how closely our genuine score distribution corresponds to our impostor score distribution. The worse the match, the

*higher*the

*D*(

*G*||

*I*) value and the easier it is to tell the two distributions apart. Consequently, the higher the RE, the easier it should be for our biometric recognition system to differentiate between genuine users and impostors based on their corresponding comparison scores, and thus the better the expected recognition accuracy. Figure 17.1 shows a simple illustration of what the relationship between

*G*and

*I*might look like for lower and higher

*D*(

*G*||

*I*) values.

One issue with using Eq. (17.1) to estimate the RE is evident when we consider what is represented by *n*. Technically, *n* is meant to denote the total number of comparison scores, and it is expected that the *G* and *I* distributions extend over the same range of scores. This, however, is not usually the case, since the overlap between the two distributions should only be partial. One consequence of this is that we will have at least one division by 0, for the range where \(I(x) = 0\) but \(G(x) \ne 0\). The result will be \(D(G||I) = \infty \). This makes sense theoretically, since if a score does not exist in *I* then it is impossible to represent it using a code based on *I*. For our purposes, however, an RE of \(\infty \) does not tell us much, since we already expect only partial overlap between *G* and *I*. So, we would like our RE metric to generate a finite number to represent the amount of information in our biometric recognition system.

Another issue with Eq. (17.1) is that this approach requires us to produce models for the genuine and impostor score distributions, *G* and *I*. Since the number of scores we have access to is generally not very large (this is particularly likely to be the case for genuine scores), it may be difficult to generate accurate models for the underlying score distributions.

## 17.3 Relative Entropy of Finger Vein Patterns

We used the NN estimator approach from [9] to estimate the RE of finger vein patterns.^{2} Section 17.3.1 describes our adopted finger vein recognition systems, and Sect. 17.3.2 presents our RE results for finger vein patterns.

### 17.3.1 Finger Vein Recognition Systems

We used two public finger vein databases for our investigation: VERA^{3} [11] and UTFVP^{4} [12]. VERA consists of two images for each of 110 data subjects’ left and right index fingers, which makes up 440 samples in total. UTFVP consists of four images for each of 60 data subjects’ left and right index, ring and middle fingers, which makes up 1,440 samples in total. Both databases were captured using the same imaging device, but with slightly different acquisition conditions. Figure 17.2 shows an example of a finger image from each database.

^{5}To extract the vein patterns from the finger images in each database, the fingers were first cropped and horizontally aligned as per [13, 14]. Next, the finger vein pattern was extracted from the cropped finger images using three well-known feature extractors: Wide Line Detector (WLD) [14], Repeated Line Tracking (RLT) [15] and Maximum Curvature (MC) [16].

The comparison between the extracted finger vein patterns was performed separately for each extractor, using the algorithm proposed in [15]. This method is based on a cross-correlation between the enrolled finger vein template and the probe template obtained during verification. The resulting comparison scores lie in the range [0, 0.5], where 0.5 represents maximum cross-correlation and thus a perfect match.

### 17.3.2 Relative Entropy of Finger Veins

We used Eq. (17.2) to calculate the RE of finger vein patterns^{6} for each of the three feature extractors (WLD, RLT, and MC) on both the VERA and UTFVP databases. One issue we faced when implementing this equation was dealing with the case where the \(d_{gg}(i)\) and/or \(d_{gi}(i)\) terms were zero. If \(d_{gi}(i) = 0\) (regardless of what value \(d_{gg}(i)\) takes), this would result in \(\hat{D}(G||I) = -\infty \), whereas \(d_{gg}(i) = 0\) (regardless of what value \(d_{gi}(i)\) takes) would result in \(\hat{D}(G||I) = \infty \). This is one of the issues we wanted to circumvent by using the NN estimator in the first place! Neither the paper that proposed the NN estimator for KL divergence [10], nor the paper that proposed using this estimator to calculate the RE of biometrics [9], suggests how to proceed in this scenario. So, we decided to add a small value (\(\epsilon \)) of \(10^{-10}\) to every \(d_{gg}(i)\) and \(d_{gi}(i)\) term that turned out to be 0. The choice of \(\epsilon \) was based on the fact that our comparison scores are rounded to 8 decimal places, so we wanted to ensure that \(\epsilon \) would be smaller than \(10^{-8}\) to minimise the impact on the original score distribution.^{7}

*every other*finger vein template in the database. The resulting RE values are summarised in Table 17.1, along with the corresponding EERs.

^{8}

Relative Entropy (RE) and Equal Error Rate (EER) for different extractors on the VERA and UTFVP databases. The RE and EER ranks refer to the rankings of the three extractors (separately for each database) in terms of the highest RE and lowest EER, respectively

DB | Extractor | RE | EER (%) | RE rank | EER rank |
---|---|---|---|---|---|

VERA | WLD | 11.8 | 9.5 | 2 | 2 |

VERA | RLT | 4.2 | 24.3 | 3 | 3 |

VERA | MC | 13.2 | 4.3 | 1 | 1 |

UTFVP | WLD | 18.9 | 2.7 | 2 | 2 |

UTFVP | RLT | 18.0 | 3.2 | 3 | 3 |

UTFVP | MC | 19.5 | 0.8 | 1 | 1 |

Since our results show the RE to be dependent upon both the feature extractor and database adopted, it would be misleading to claim a universal finger vein RE estimate; rather, it makes more sense for the RE to be system-specific.

Intuitively, we can see that, the higher the RE, the greater the amount of discriminatory information, and thus the greater the expected recognition capabilities of the underlying system. This intuition is confirmed when we compare the REs and EERs of the different systems in Table 17.1, in terms of the RE-based versus EER-based rankings. From this analysis, it is evident that the ranking of the three extractors for each database is the same regardless of whether that ranking is based on the RE or the EER. In particular, MC has the highest RE and lowest EER, while RLT has the lowest RE and highest EER. This implies that the most discriminatory information is contained in finger vein patterns that have been extracted using the MC extractor, and the least discriminatory information is contained in RLT-extracted finger veins. These results suggest the possibility of using the REs of different finger vein recognition systems to rank the systems according to the amount of discriminatory information and thus their expected recognition accuracies. Consequently, it appears reasonable to conclude that the RE estimator is a reliable indicator of the amount of discriminatory information in a finger vein recognition system.

While RE quantifies the amount of discriminatory information in a biometric system, it is difficult to gauge what exactly this number, on its own, means. For example, what exactly does *x* bits of discriminatory information signify, and is a *y*-bit difference in the REs of two biometric systems significant? Furthermore, benchmarking different biometric systems in terms of their RE is not straightforward, since the RE estimate depends on both the comparison score range as well as on the number of genuine (\(N_g\)) and impostor scores (\(N_i\)) for each database and experimental protocol. Consequently, REs reported for different biometric systems usually do not lie in the same [\(RE_{\min }\), \(RE_{\max }\)] range.^{9} To help us better understand the meaning of the RE metric in the context of a biometric system, as well as to enable fair cross-system RE benchmarking, Sect. 17.4 adapts Eq. (17.2) to propose a *normalised* RE metric.

## 17.4 Normalised Relative Entropy

This section proposes a normalised version of the RE (NRE), based on the NN estimator in Eq. (17.2). The reason for this normalisation is to help us interpret the RE in a more intuitive way, and to enable fair benchmarking of different biometric systems in terms of their RE.

Due to the “min–max” operation in Eq. (17.3), the NRE will lie in the range [0.00, 1.00]. We can thus interpret the NRE as follows. An NRE of 0.00 would suggest that the system in question contains zero discriminative information (i.e. recognition would actually be impossible), whereas an NRE of 1.00 would indicate that the system contains the maximum amount of discriminative information possible for that system (i.e. the recognition accuracy would be expected to be perfect).

In general, therefore, we can look at the NRE as providing an indication of the proportion of the maximum amount of discriminatory information that the corresponding biometric system contains. An NRE of 0.50, for example, would indicate that the biometric system achieves only 50% of the maximum attainable recognition accuracy. Therefore, the higher the NRE, the better the expected recognition accuracy of the biometric system we are measuring.

Relative Entropy (RE) and Normalised Relative Entropy (NRE) for different finger vein recognition systems

System | RE | NRE |
---|---|---|

VERA-WLD | 11.8 | 0.48 |

VERA-RLT | 4.2 | 0.34 |

VERA-MC | 13.2 | 0.50 |

UTFVP-WLD | 18.9 | 0.58 |

UTFVP-RLT | 18.0 | 0.56 |

UTFVP-MC | 19.5 | 0.59 |

Note that the first column of Table 17.2 refers to the finger vein recognition system constructed using the specified database and feature extractor. We have pooled the databases and extractors into “systems” now to indicate that the NRE values can be benchmarked *across systems* (as opposed to, for example, in Table 17.1, where the databases were separate to indicate that RE-based benchmarking of the different extractors should be *database-specific*).

As an example of how the NRE results from Table 17.2 can be interpreted, let us compare the NRE of VERA-RLT to that of UTFVP-MC. The NRE of 0.34 for VERA-RLT tells us that this system achieves only 34% of the maximum attainable discrimination capability. Comparatively, the UTFVP-MC system contains 59% of the maximum amount of discriminative information. So, we could conclude that the UTFVP-MC finger vein recognition system contains 25% more discriminatory information than the VERA-RLT system.

Using the NRE also helps us gauge the significance of the differences in the REs across different biometric systems. For example, if we look at the RE on its own for the UTFVP-WLD and UTFVP-MC systems in Table 17.2, we can see that the latter system’s RE is 0.6 bits larger than the former system’s RE. It is difficult to tell, however, whether or not this is a significant difference. If we then look at the NREs of the two systems, we can see that their difference is only 0.01. This indicates that the 0.6-bit difference between the two systems’ REs is not too significant in terms of the proportion of the maximum discriminatory information the two systems contain. On the other hand, the 15.3-bit difference in the REs between the VERA-RLT and UTFVP-MC systems seems much more significant, and we may be tempted to conclude that the latter system contains about five times more discriminative information than the former system. Looking at the two systems’ NREs, we do see a fairly significant difference, but we would have to conclude that the UTFVP-MC system contains not five times, but two times, more discriminative information than the VERA-RLT system.

In this section, we have shown how the NRE can be used for RE-based benchmarking of different finger vein recognition systems, for which comparison scores were evaluated on different databases. The main reason for using the NRE in our case was thus to conduct fair cross-database system benchmarking. Our proposed NRE metric, however, can also be used to fairly benchmark the REs of systems based on different biometric modalities, tested on different databases using different experimental protocols. For example, part of our future work will involve benchmarking the NRE of our best finger vein recognition system, UTFVP-MC, against NREs of systems based on different types of biometrics. This makes the proposed NRE metric a flexible tool for both quantifying and benchmarking the amount of discriminative information contained in different biometric systems.

## 17.5 Discussion

In this section, we begin by presenting a discussion on an important aspect of the NRE, which supports its adoption in the biometrics community. We then discuss two potential issues that may arise when calculating the NRE, and we suggest the means of dealing with them. Sections 17.5.1, 17.5.2 and 17.5.3, respectively, tackle these three discussion points.

### 17.5.1 NRE as a Complement to EER

So far, we have shown how the RE can be used to measure the amount of discriminatory information in finger vein recognition systems. We also proposed the NRE metric to fairly benchmark the REs across different biometric systems. In this section, we discuss how an NRE estimate could complement the EER to provide a more complete picture of the performance of a biometric recognition system.

In Sect. 17.2, we explained how, in the context of a biometric recognition system, the RE metric provides some indication of how closely our genuine score distribution matches our impostor score distribution. Let us explore the meaning of this by considering Eq. (17.2). Equation (17.2) tells us that we are attempting to estimate the relative entropy of a set of genuine comparison scores (*G*) in terms of a set of impostor comparison scores (*I*). In other words, we wish to quantify the “closeness” of these two sets^{10} of scores. The \(d_{gi}\) and \(d_{gg}\) terms represent the distance between a genuine score and its closest score in the set of impostor and genuine scores, respectively. Larger \(d_{gi}\) values will result in *larger* RE results, whereas larger \(d_{gg}\) values will result in *smaller* RE results.^{11} We can thus see that larger REs favour a larger inter-class variance (i.e. greater separation between genuine comparison trials and impostor trials) and a smaller intra-class variance (i.e. smaller separation between multiple biometric samples from the same biometric instance). This makes the RE suitable as a measure of the performance of a biometric recognition system: the larger the RE value, the better the recognition accuracy. The best (highest) RE would, therefore, be obtained in the case where all the \(d_{gi}\) values are as large as possible, while the \(d_{gg}\) values are as small as possible, and vice versa for the worst (lowest) RE.

*I*, and a set of genuine scores,

*G*. The larger the intersection between

*I*and

*G*, the smaller the \(d_{gi}\) values and thus the lower the RE. Conversely, the smaller the intersection between the two sets, the greater the \(d_{gi}\) values and thus the higher the RE. So far, the RE metric appears to tell us the same thing as the EER, since a smaller EER indicates less overlap between genuine and impostor comparison scores, while a larger EER indicates more overlap. Where the two metrics differ, however, is in the scenario where

*I*and

*G*are completely separated. In this case, the further apart the two sets of scores are the higher the resulting RE. The EER, however, would be 0% regardless of whether the separation is small or large. Imagine if we had to benchmark two biometric systems, both of which had complete separation between the genuine and impostor comparison scores, but where for one system the separation was much larger than for the other, as illustrated

^{12}in Fig. 17.5. If we considered only the EER, it would indicate that the two systems are the same (i.e. both have an EER of 0%). The NRE,

^{13}however, would clearly indicate that the system with greater separation is better in terms of distinguishing genuine trials from impostors, since the NRE value would be higher for that system. In this case, complementing the EER with an NRE estimate would provide a more complete picture of the system comparison. This could come in useful particularly in situations where the data used for testing the biometric system was collected in a constrained environment, in which case an EER of 0% could be expected. The NRE, on the other hand, would provide us with more insight into the separation between the genuine and impostor score distributions.

*I*is the same and the separation (or overlap) between

*I*and

*G*is the same, but

*G*differs. In particular, in the first system the genuine scores are closer together, while in the second system the genuine scores are further apart from each other. Figure 17.6 illustrates this scenario.

^{14}In this case, since the separation between

*I*and

*G*for both systems is the same, the EER would also be the same, thereby indicating that one system is just as good as the other. The NRE, however, would be smaller for the second system due to the larger \(d_{gg}\) values. The NRE would thus indicate that the larger intra-class variance in the second system makes this system less preferable in terms of biometric performance when compared to the first system, for which the genuine scores are closer together and thus the intra-class variance is smaller. Using both NRE and EER together, we could thus conclude that, although both systems can be expected to achieve the same error rate, the system with the smaller intra-class variance would be a superior choice.

When choosing between the EER and NRE metrics for evaluating the performance of a biometric system, we would still recommend using the EER as the primary one, since it is more practical in providing us with a solid indication of our system’s expected error rate. The NRE, however, would be a useful complement to the EER when we are trying to decide on the best of *n* biometric systems that have the *same* EER.

### 17.5.2 Selecting the \(\epsilon \) Parameter

RE and NRE for MC-extracted finger veins from UTFVP, when \(\epsilon \) is varied in the range \([10^{-12}, 10^{-8}]\). Note that, for consistency with Table 17.2, RE and NRE values are rounded to 1 d.p. and 2 d.p., respectively

\(\epsilon \) | RE | NRE |
---|---|---|

\(10^{-8}\) | 19.5 | 0.62 |

\(10^{-9}\) | 19.5 | 0.60 |

\(10^{-10}\) | 19.5 | 0.59 |

\(10^{-11}\) | 19.5 | 0.58 |

\(10^{-12}\) | 19.5 | 0.57 |

From Fig. 17.7 and Table 17.3, we can see that, while the choice of \(\epsilon \) does affect the RE and NRE to some degree (more specifically, the RE and NRE decrease as \(\epsilon \) decreases^{15}), this effect does not appear to be significant. So, we may conclude that, as long as the \(\epsilon \) parameter is sensibly chosen (i.e. smaller than the comparison scores, but not so small that it is effectively zero), then the RE and NRE estimates should be reasonable.

### 17.5.3 Number of Nearest Neighbours

The method proposed in [9] to estimate the RE of biometrics uses only the *first* nearest genuine and impostor neighbours of each genuine score. An issue with this approach is that it makes the RE estimate highly dependent on any single score, even if that score is an outlier. This might be particularly problematic if we do not have a large number of scores to work with, which is often the case.

*k*nearest neighbours, where \(k > 1\), then average the resulting \(d_{gg}(i)\) and \(d_{gi}(i)\) values over these

*k*neighbours prior to estimating the RE. This would introduce some smoothing to the underlying score distributions, thereby stabilising the RE estimates. While the effect of

*k*on the RE, and therefore NRE, is difficult to generalise since it would, in practice, be dependent on the biometric system in question, we wished to test the effect of the choice of

*k*on the RE and NRE of our best finger vein recognition system, that obtained when using MC-extracted finger veins from the UTFVP database. Figure 17.8 shows plots of the RE and NRE versus

*k*, when

*k*increases from 1 to 5. For convenience, Table 17.4 summarises the RE and NRE values from Fig. 17.8. Note that, for this experiment, \(\epsilon = 10^{-10}\), as for the RE and NRE experiments in Sects. 17.3 and 17.4.

From Fig. 17.8 and Table 17.4, it is evident that increasing *k* tends to decrease both the RE and NRE, but the decrease is not drastic for \(k \le 5\). This decrease makes sense, since a larger *k* means a greater degree of smoothing, which decreases the effects of individual comparison scores. Another consequence of using a larger *k* would be that the effect of the \(\epsilon \) parameter on RE and NRE would be expected to be less pronounced. This is because a larger *k* means that a larger number of neighbouring scores are averaged when calculating the RE and NRE, so we are less likely to encounter zero average scores than in the scenario where only *one* nearest neighbouring score is considered. Keeping the aforementioned points in mind, it is important to sensibly tune the *k* and \(\epsilon \) parameters depending on the biometric system in question (e.g. if there are outlier scores, use \(k > 1\), and select \(\epsilon \) based on the score precision, as discussed in Sect. 17.5.2). Furthermore, we urge researchers adopting the RE and NRE measures to be transparent about their selection of these parameters to ensure fair system comparisons across the biometrics community.

Note that the NN estimator on which Eq. (17.2) is based [10] *is* actually a *k*-NN estimator, where *k* denotes the number of nearest neighbours. It is not clear, however, whether the proposed *k*-NN estimator is based on *averaging* the *k* nearest neighbouring scores, as we have done for Fig. 17.8 and Table 17.4, or whether the authors meant that *only* the *k*th neighbour should be used. If their intention is the latter, then our averaging approach represents an effective new way of stabilising the *k*-NN estimator for RE measures.

## 17.6 Conclusions and Future Work

This chapter represents the first attempt at estimating the amount of information in finger vein biometrics in terms of score-based Relative Entropy (RE), using the previously proposed Nearest Neighbour estimator. We made five important contributions.

First, we showed that the RE estimate is system-specific. In our experiments, the RE differed across finger vein recognition systems employing different feature extractors and different testing databases. For this reason, we refrain from claiming a universal finger vein RE estimate, since this would be misleading.

Second, we showed that the RE can be used to rank different finger vein recognition systems, which are tested on the same database using the same experimental protocol (in our case, the difference was the feature extractor employed), in terms of the amount of discriminative biometric information available. The ranking was shown to be comparable to an EER-based ranking, which implies that the RE estimate is a reliable indicator of the amount of discriminatory information in finger vein recognition systems.

Third, we proposed a new metric, the Normalised Relative Entropy (NRE), to help us gauge the significance of individual RE scores as well as to enable fair benchmarking of different biometric systems (in particular, systems tested on different databases using different experimental protocols) in terms of their RE. The NRE lies in the range [0.00, 1.00] and represents the proportion of the maximum amount of discriminatory information that is contained in the biometric system being measured. The higher the NRE, the better the system is expected to be at distinguishing genuine trials from impostors.

Fourth, we discussed how the NRE metric could be a beneficial complement to the EER in ranking different biometric systems in terms of their discrimination capabilities. The NRE would be particularly useful in choosing the best of *n* biometric systems that have the same EER.

Finally, we discussed two potential issues in calculating the RE and NRE, namely, the effects of the \(\epsilon \) parameter and the number of nearest neighbours (*k*) used for computing the genuine–genuine and genuine–impostor score differences. We showed that, as long as \(\epsilon \) is sensibly selected, its effect on the RE and NRE is unlikely to be significant. We also showed that increasing the number of nearest score neighbours may be expected to slightly decrease the RE and NRE, but the upside is that using a larger number of nearest neighbours would help to dilute the effects of outliers among the genuine and impostor comparison scores. We concluded by suggesting that \(\epsilon \) and *k* be tuned according to the biometric system being evaluated and that researchers be transparent in terms of reporting their selection of these two parameters.

At the moment, our primary aim for future work in this direction is to use our proposed NRE metric to benchmark finger vein recognition systems against systems based on other biometric modalities, in terms of the amount of discriminatory information contained in each system.

## Footnotes

- 1.
For a real-life example, see: http://money.cnn.com/2015/09/23/technology/opm-fingerprint-hack.

- 2.
Code available at https://gitlab.idiap.ch/bob/bob.chapter.fingerveins_relative_entropy.

- 3.
- 4.
- 5.
- 6.
Note: \(RE = \hat{D}(G||I)\).

- 7.
This choice of \(\epsilon \) may not necessarily be optimal, but it seems sensible.

- 8.
Note that we have chosen to compare the RE to the EER, because the EER is a widely used metric for evaluating the overall recognition accuracy (in terms of the trade-off between the False Match Rate (FMR) and False Non-Match Rate (FNMR)) of a biometric recognition system. The comparison seems appropriate, since RE aims to provide us with an idea of a biometric system’s overall discrimination capability.

- 9.
For the finger vein systems we used, the comparison scores for both the VERA and UTFVP databases lie in the same range of [0, 0.5]. However, the \(N_g\) values across the two databases are different as are the \(N_i\) values. Consequently, the [\(RE_{\min }\), \(RE_{\max }\)] range is not the same for both databases, meaning that we cannot fairly compare the RE results across the two databases.

- 10.
Note: We are purposely using the word “set” as opposed to “distribution”, since the NN estimator in Eq. (17.2) works directly on the scores as opposed to distributions representing the scores.

- 11.
Assume constant \(N_g\) and \(N_i\) values.

- 12.
Note: The only reason for using probability density plots in this figure is to present a cleaner illustration of our point. Probability density functions are

*not*used to represent genuine and impostor score distributions for the NRE calculation. - 13.
When benchmarking different biometric systems, the NRE should be used instead of the RE to ensure that the benchmarking is fair. The only exception to this rule would be in the case where the different systems had the same comparison score range, and the same \(N_g\) and \(N_i\) values, in which case the resulting REs would lie in the same [\(RE_{\min }\), \(RE_{\max }\)] range.

- 14.
Note: In Fig. 17.6, the EER for both systems is 0%; however, it could also be possible for both systems to have the same non-zero EER. In this case,

*I*and*G*would partially overlap. - 15.
In general, the RE, and thus the NRE, would be expected to

*decrease*with a decrease in \(\epsilon \) when there are more \(d_{gi}\) than \(d_{gg}\) zero score differences. Alternatively, the RE, and thus the NRE, would be expected to*increase*with a decrease in \(\epsilon \) when there are more \(d_{gg}\) than \(d_{gi}\) zero score differences.

## Notes

### Acknowledgements

The authors would like to acknowledge the following sources of funding for supporting this work: the Secure Access Control over Wide Area Network (SWAN) project, the German Federal Ministry of Education and Research (BMBF) and the Hessen State Ministry for Higher Education, Research and the Arts (HMWK) within the Center for Research in Security and Privacy (CRISP).

## References

- 1.Ye Y, Zheng H, Ni L, Liu S, Li W (2016) A study on the individuality of finger vein based on statistical analysis. In: 2016 international conference on biometrics (ICB), pp 1–5, June 2016Google Scholar
- 2.Yanagawa T, Aoki S, Ohyama T (2007) Human finger vein images are diverse and its patterns are useful for personal identification. MHF Prepr Ser 12:1–7zbMATHGoogle Scholar
- 3.Jeffers J, Arakala A, Horadam KJ (2010) Entropy of feature point-based retina templates. In: 2010 20th international conference on pattern recognition, pp 213–216, Aug 2010Google Scholar
- 4.Daugman J (2004) How iris recognition works. IEEE Trans Circuits Syst Video Technol 14(1):21–30CrossRefGoogle Scholar
- 5.Krivokuca V, Marcel S (2018) Towards quantifying the entropy of fingervein patterns across different feature extractors. In: 2018 IEEE 4th international conference on identity, security, and behavior analysis (ISBA), pp 1–8, Jan 2018Google Scholar
- 6.Takahashi K, Murakami T (2010) A metric of information gained through biometric systems. In: Proceedings of the 2010 20th international conference on pattern recognition. IEEE Computer Society, pp 1184–1187Google Scholar
- 7.Sutcu Y, Tabassi E, Sencar HT, Memon N (2013) What is biometric information and how to measure it? In: 2013 IEEE international conference on technologies for homeland security (HST), pp 67–72, Nov 2013Google Scholar
- 8.Adler A, Youmaran R, Loyka S (2006). Towards a measure of biometric information. In 2006 Canadian conference on electrical and computer engineering, pp 210–213, May 2006Google Scholar
- 9.Sutcu Y, Sencar HT, Memon N (2010) How to measure biometric information? In : 2010 20th international conference on pattern recognition, pp 1469–1472, Aug 2010Google Scholar
- 10.Wang Q, Kulkarni SR, Verdu S (2009) Divergence estimation for multidimensional densities via \(k\)-nearest-neighbor distances. IEEE Trans Inf Theory 55(5):2392–2405MathSciNetCrossRefGoogle Scholar
- 11.Vanoni M, Tome P, El-Shafey L, Marcel S (2014) Cross-database evaluation using an open finger vein sensor. In: 2014 IEEE workshop on biometric measurements and systems for security and medical applications (BIOMS) proceedings, pp 30–35, Oct 2014Google Scholar
- 12.Ton BT, Veldhuis RNJ (2013) A high quality finger vascular pattern dataset collected using a custom designed capturing device. In: 2013 international conference on biometrics (ICB), pp 1–5, June 2013Google Scholar
- 13.Lee EC, Lee HC, Park KR (2009) Finger vein recognition using minutia-based alignment and local binary pattern-based feature extraction. Int J Imaging Syst Technol 19(3):179–186CrossRefGoogle Scholar
- 14.Huang B, Dai Y, Li R, Tang D, Li W (2010) Finger-vein authentication based on wide line detector and pattern normalization. In: 2010 20th international conference on pattern recognition, pp 1269–1272, Aug 2010Google Scholar
- 15.Miura N, Nagasaka A, Miyatake T (2004) Feature extraction of finger-vein patterns based on repeated line tracking and its application to personal identification. Mach Vis Appl 15(4):194–203CrossRefGoogle Scholar
- 16.Miura N, Nagasaka A, Miyatake T (2007) Extraction of finger-vein patterns using maximum curvature points in image profiles. IEICE Trans Inf Syst 90(8):1185–1194CrossRefGoogle Scholar

## Copyright information

**Open Access** This chapter is licensed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

The images or other third party material in this chapter are included in the chapter's Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the chapter's Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.