When we use the word ‘biometrics’ we are referring to the unique, measurable characteristic of a human being. This may be a physical or behavioral characteristic.
Essentially operate in a similar way. First, a biometric system captures a sample of the biometric characteristic (biometric sample). Unique features are then extracted by the system and converted into a mathematical code (biometric data). The biometric data is then stored as the biometric template (also known as template or reference template) for that person. When an identity needs checking, the person interacts with the biometric system for a second time. A new biometric sample is taken. This is compared to the template. If the template and the new sample match, the person’s identity is confirmed.
False Rejection and False Acceptance
The biometrics industry has for a number of years used two performance measurements to rank a biometric system’s level of matching accuracy. This focuses on the system’s ability to allow access to authorized users and deny access to those who are unauthorized. These are known as the false rejection rate (FRR) and false acceptance rate (FAR). The FRR is sometimes referred to as the Type I error rate while the FAR is the Type II error rate. The false rejection rate is concerned with the number of instances an authorized individual is falsely rejected by the system. The false acceptance rate refers to the number of instances a non-authorized individual is falsely accepted by the system.