Score normalization in multimodal biometric systems

Abstract

Multimodal biometric systems consolidate the evidence presented by multiple biometric sources and typically provide better recognition performance compared to systems based on a single biometric modality. Although information fusion in a multimodal system can be performed at various levels, integration at the matching score level is the most common approach due to the ease in accessing and combining the scores generated by different matchers. Since the matching scores output by the various modalities are heterogeneous, score normalization is needed to transform these scores into a common domain, prior to combining them. In this paper, we have studied the performance of different normalization techniques and fusion rules in the context of a multimodal biometric system based on the face, fingerprint and hand-geometry traits of a user. Experiments conducted on a database of 100 users indicate that the application of min–max, z-score, and tanh normalization schemes followed by a simple sum of scores fusion method results in better recognition performance compared to other methods. However, experiments also reveal that the min–max and z-score normalization techniques are sensitive to outliers in the data, highlighting the need for a robust and efficient normalization procedure like the tanh normalization. It was also observed that multimodal systems utilizing user-specific weights perform better compared to systems that assign the same set of weights to the multiple biometric traits of all users.

Introduction

Biometric systems make use of the physiological and/or behavioral traits of individuals, for recognition purposes [1]. These traits include fingerprints, hand-geometry, face, voice, iris, retina, gait, signature, palm-print, ear, etc. Biometric systems that use a single trait for recognition (i.e., unimodal biometric systems) are often affected by several practical problems like noisy sensor data, non-universality and/or lack of distinctiveness of the biometric trait, unacceptable error rates, and spoof attacks [2]. Multimodal biometric systems overcome some of these problems by consolidating the evidence obtained from different sources [3]. These sources may be multiple sensors for the same biometric (e.g., optical and solid-state fingerprint sensors), multiple instances of the same biometric (e.g., fingerprints from different fingers of a person), multiple snapshots of the same biometric (e.g., four impressions of a user's right index finger), multiple representations and matching algorithms for the same biometric (e.g., multiple face matchers like PCA and LDA), or multiple biometric traits (e.g., face and fingerprint).

The use of multiple sensors addresses the problem of noisy sensor data, but all other potential problems associated with unimodal biometric systems remain. A recognition system that works on multiple instances of the same biometric can ensure the presence of a live user by asking the user to provide a random subset of biometric measurements (e.g., left index finger followed by right middle finger). Multiple snapshots of the same biometric, or multiple representations and matching algorithms for the same biometric may also be used to improve the recognition performance of the system. However, all these methods still suffer from many of the problems faced by unimodal systems. A multimodal biometric system based on different traits is expected to be more robust to noise, address the problem of non-universality, improve the matching accuracy, and provide reasonable protection against spoof attacks. Hence, the development of biometric systems based on multiple biometric traits has received considerable attention from researchers.

In a multimodal biometric system that uses different biometric traits, various levels of fusion are possible: fusion at the feature extraction level, matching score level or decision level (as explained in Section 2). It is difficult to consolidate information at the feature level because the feature sets used by different biometric modalities may either be inaccessible or incompatible. Fusion at the decision level is too rigid since only a limited amount of information is available at this level. Therefore, integration at the matching score level is generally preferred due to the ease in accessing and combining matching scores.

In the context of verification, fusion at the matching score level can be approached in two distinct ways. In the first approach the fusion is viewed as a classification problem, while in the second approach it is viewed as a combination problem. In the classification approach, a feature vector is constructed using the matching scores output by the individual matchers; this feature vector is then classified into one of two classes: “Accept” (genuine user) or “Reject” (impostor). In the combination approach, the individual matching scores are combined to generate a single scalar score which is then used to make the final decision. Both these approaches have been widely studied in the literature. Ross and Jain [4] have shown that the combination approach performs better than some classification methods like decision tree and linear discriminant analysis. However, no single classification or combination scheme works well under all circumstances. In this paper, we use the combination approach to fusion and address some of the issues involved in computing a single matching score given the scores of different modalities. Since the matching scores generated by the different modalities are heterogeneous, normalization is required to transform these scores into a common domain before combining them. While several normalization techniques have been proposed, there has been no detailed study of these techniques. In this work, we have systematically studied the effects of different normalization schemes on the performance of a multimodal biometric system based on the face, fingerprint and hand-geometry modalities.

The rest of the paper is organized as follows: Section 2 presents a brief overview of the various approaches used for information fusion in multimodal biometrics and motivates the need for score normalization prior to matching score fusion. Section 3 describes different techniques that can be used for the normalization of scores obtained from different matchers. The experimental results are presented in Section 4 and we have outlined our conclusions in Section 5.