Score Selection Techniques for Fingerprint Multi-modal Biometric Authentication

Abstract

Fingerprints are one of the most used biometrics for automatic personal authentication. Unfortunately, it is often difficult to design fingerprint matchers exhibiting the performances required in real applications. To meet the application requirements, fusion techniques based on multiple matching algorithms, multiple fingerprints, and multiple impressions of the same fingerprint, have been investigated. However, no previous work has investigated selection strategies for biometrics. In this paper, a score selection strategy for fingerprint multi-modal authentication is proposed. For each authentication task, only one score is dynamically selected so that the genuine and the impostor users' scores distributions are mainly separated. Score selection is performed by first estimating the likelihood that the input pattern is an impostor or a genuine user. Then, the min score is selected in case of an impostor, while the max score is selected in case of a genuine user. Reported results show that the proposed selection strategy can provide better performances than those of commonly used fusion rules.

Dynamic Score Selection for Fusion of Multiple Biometric Matchers

“…In order to produce distribution of genuine and impostor scores that allows attaining smaller errors than those of individual matchers, we have defined the ideal score selector as the ideal matcher selector that selects the maximum score for genuine users and the minimum score for impostor users [3,4]. In other words the output s i, * of the ideal selector for user u i is computed as follows:…”

“…For each authentication task, "dynamic selection" chooses the most suited matching scores among those produced by the available systems. In [3] the authors proposed an ideal selection mechanism tailored to biometric systems, that allows attaining smaller error rates, i.e. the False Matching Rate (FMR, i.e.…”

“…Combination of multiple biometric systems is typically performed at the score level, and different fusion techniques (e.g., average, product, sum, etc) have been successfully applied [6] [10]. "Dynamic selection" mechanisms have been proposed as an alternative to the combination by fusion techniques [3]. For each authentication task, "dynamic selection" chooses the most suited matching scores among those produced by the available systems.…”