No abstract

No abstract

Biometric identification referes to idetifying an individual based on his or her physilogical or beavioral characteristics. The use of more than one biometric identfiers in a biometric system, called the multimodal biometric system, increases the overall system accuracy and hence increase security, as well as reduce the enrollment problems. An effective and appropriate fusion strategy is needed to integrate different biometric information in such multimodal systems. This chapter provides an in-depth overview of traditional multimodal biometric systems and current trends in multimodal biometric fusion. Various approaches of rank level fusion, which is an not heavily investigated by researchers yet, are also illustrated in details in this chapter. Pros and cons of these rank fusion approaches are discussed which can be helpful for large scale multimodal biometric system deployment. IntroductionControlling access to prohibited areas and protecting important national or public information are some of the main activities of security and intelligence services of many countries of the world. Often, to decide if a person is allowed to access a prohibited area, a biometric system is employed. A biometric system is an automated method of recognizing a person based on a physiological (face, iris, ear etc.) and/or behavioral (signature, voice, typing patterns etc.) characteristics [1]. Other applications of biometrics systems include e-commerce, access to computer networks, online banking, border control, parenthood determination, medical records management, and welfare disbursement.The optimal biometric recognition method is one having the properties of distinctiveness, universality, permanence, acceptability, collect ability, and resistance to circumvention [2]. No existing biometric system simultaneously meets all of these requirements; however the use of more than one biometric can help to develop a system which approaches those goals [3]. The advantages of multimodal systems stem from the fact that there are multiple sources of information. The most prominent implications of this are increased accuracy, fewer enrolment problems and enhanced security. All multimodal biometric systems need a fusion module that takes individual data and combines it

No abstract

No abstract