User Identification is one of the key features assuring that the system or application only performs commands which are properly authorized. The most widely used authentication type is password, but with development of information technologies and security protection algorithms, systems and applications start to use authentication based on the biometric factors.
Using biometrics effectively eliminate possible risks associated with less advanced technologies that are based on what a person have or know rather than whom a person really is [1]. It is a very attractive and popular technology, because it can be integrated into any application or system requiring security or access control.
The speaker identification tends to provide basic identification of the possible users located in the system installation area. The face detection approach aims to provide more reliable user identification based on users’ faces which contain far more characteristics that can be parameterized in comparison to the voice identification approach. Additionally, the 3D face recognition further extends the possibilities of feature extraction in order to more precisely identify particular persons and can be thus used for the highest level authentication (and authorization) for the most demanding applications (e.g. bank account login, etc.). For security reasons, 3D face recognition authentication can be enhanced with e.g. eye movement tracking or iris recognition. This approach may simulate multi-factor authentication (login plus token) necessary for the highest level authentication.
However, biometrics have also drawbacks. Iris recognition is extremely accurate, but expensive to implement and not very accepted by people. Fingerprints are reliable and non-intrusive, but not suitable for non-collaborative individuals. On the contrary, face recognition seems to be a good compromise between reliability and social acceptance [1].