Increased and Reliable Recognition Performance

The optimal biometric system is one having the properties of distinctiveness, universality, permanence, acceptability, collectability, and security. As we saw in the introductory chapters, no existing biometric security system simultaneously meets all of these requirements. Despite tremendous progress in the field, over the last decades researchers noticed that while a single biometric trait might not always satisfy secure system requirements, the combination of traits from different biometrics will do the job. The key is in aggregation of data and intelligent decision making based on responses received from individual (unimodal) biometric systems.

Thus, Multimodal biometrics emerged as a new and highly promising approach to biometric knowledge representation, which strives to overcome problems of individual biometric matchers by consolidating the evidence presented by multiple biometric traits. As an example, a multimodal system may use both face recognition and signature to authenticate a person. Due to reliable and efficient security solutions in the security critical applications, multimodal biometric systems have evolved over last decade as a viable alternative to the traditional unimodal security systems.

The advantages of multimodal biometric systems over unimodal systems are mainly due to utilization of more than one information source. Figure 1 shows a sample multimodal biometric system. The most prominent implications of this are increased and reliable recognition performance, fewer enrolment problems, and enhanced security.

A multimodal system allows for a greater level of assurance of a proper match in verification and identification modes. As multimodal biometric systems use more than one biometric trait, each of those traits can offer additional evidence about the authenticity of any identity claim. For example, the gaits (the patterns of movements) of two persons of the same family (or coincidentally of two different persons) can be similar. In this scenario, a unimodal biometric system based only on gait pattern analysis may results in false recognition. If the same biometric system also includes fingerprint matching, the system would results in increased recognition rate, as it is very unlikely that two different persons have same gait and fingerprint patterns.