Performance analysis of multimodal biometric fusion

Biometrics is constantly evolving technology which has been widely used in many official and commercial identification applications. In fact in recent years biometric-based authentication techniques received more attention due to increased concerns in security. Most biometric systems that are currently in use typically employ a single biometric trait. Such systems are called unibiometric systems. Despite considerable advances in recent years, there are still challenges in authentication based on a single biometric trait, such as noisy data, restricted degree of freedom, intra-class variability, non-universality, spoof attack and unacceptable error rates. Some of the challenges can be handled by designing a multimodal biometric system. Multimodal biometric systems are those which utilize or are capable of utilizing, more than one physiological or behavioural characteristic for enrolment, verification, or identification. In this thesis, we propose a novel fusion approach at a hybrid level between iris and online signature traits. Online signature and iris authentication techniques have been employed in a range of biometric applications. Besides improving the accuracy, the fusion of both of the biometrics has several advantages such as increasing population coverage, deterring spoofing activities and reducing enrolment failure. In this doctoral dissertation, we make a first attempt to combine online signature and iris biometrics. We principally explore the fusion of iris and online signature biometrics and their potential application as biometric identifiers. To address this issue, investigations is carried out into the relative performance of several statistical data fusion techniques for integrating the information in both unimodal and multimodal biometrics. We compare the results of the multimodal approach with the results of the individual online signature and iris authentication approaches. This dissertation describes research into the feature and decision fusion levels in multimodal biometrics.