18-12-2009, 03:36 PM
Is this the person who he or she claims to be? Nowadays this question arises incessantly. In different organizations like financial services, e-commerce, telecommunication, government, traffic, health care the security issues are more and more important. It is important to verify that people are allowed to pass some points or use some resources. The security issues are arisen quickly after some crude abuses. For these reason, organizations are interested in taking automated identity authentication systems, which will improve customer satisfaction and operating efficiency. The authentication systems will also save costs and be more accurate that a human being.Basically there are three different methods for verifying identity: (i) possessions, like cards, badges, keys; (ii) knowledge, like userid, password, Personal Identification Number (PIN); (iii) biometrics like fingerprint, face, ear. Biometrics is the science of identifying or verifying the identity of a person based on physiological or behavioral characteristics. Biometrics offer much higher accuracy than the more traditional ones. Possession can be lost, forgot or replicated easily. Knowledge can be forgotten. Both possessions and knowledge can be stolen or shared with other people. In biometrics these drawbacks do exist only in small scale.The ear has been proposed as a biometric (Victor et al., 2002). The difficulty is that we have several adjectives to describe e.g. faces but almost none for ears. We all can recognize people from faces, but we hardly can recognize anyone from ears.The paper is organized as follows: we start with defining basic terminology of biometrics, then present the structure of the ear and categories of different methods of ear biometrics. The principal component analysis (PCA) algorithm in ear recognition is presented with two different cases. The application scenarios and discussion about error rates in ear identification are presented.
