Biometric Recognition Systems are used to identify an individual person based on the feature vectors of any one of the biometric that the person possesses. These systems are person authorized systems hence offer more secure and convenient process of identification compared to alternative methods of identification. The computer based security systems are used in various commercial, civilian and forensic applications. Each person has to establish the identity ranging from drivers’ license to gaining entry into a country to the passport. The biometric system uses the individual’s physical characteristics like fingerprint, hand geometry, face, voice or iris. They are more reliable and secure as they provides the access to authorized users in their physical presence. Looking at biometric systems in a more general way will reveal certain things all biometric-based authentication systems have in common.
In general such systems work in two modes:
Enrollment Mode: In which biometric user data is acquired. This is mostly done with some type of biometric reader. Afterwards the gathered information is stored in a database where it is labeled with a user identity (e.g. id number, name) to facilitate authentication.
Authentication Mode: Again biometric user data is acquired first and used by the system to either verify the users claimed identity or to identify who the user is. While identification involves the process of comparing the user’s biometric data against all users in the database, the process of verification compares the biometric data against only those entries in the database which are corresponding to the users claimed identity.
In general one can consider the verification of the identity of a person a two-class problem:
• either the person is who he/she claims to be (client)
• or the person fails to be the one he/she claims to be (impostor)
A simple biometric system consists of four modules:
1. Sensor Module: This module acquires biometric user data. Examples of sensor module would be a retina scanner or a fingerprint sensor.
2. Feature Extraction Module: This module is responsible for extracting feature values of a biometric trait. If hand geometry would be used as a biometric trait then feature values would include width of fingers at various locations, width of the palm, thickness of the palm, length of fingers etc.
3. Matching Module: The matching module compares the acquired biometric features against those stored in a database.
4. Decision-Making Module: The user’s identity is either established or a claimed identity is accepted or rejected.
This is done based on the results of the matching modules. Since we are dealing with a binary decision scheme it is obvious that the decision-making module can make two kinds of errors. The errors, which can be made in the process of verification, are called:
• False Rejection (FR): when an actual client gets identified as an impostor.
• False Acceptance (FA): when an actual impostor gets identified as a client.