10 Factors That Affect Biometrics Performance
Biometric performance can make or break a technological security solution. As someone who’s responsible for the security of a building or campus, if you’re not happy with your security solutions these factors may be your problem.
All biometrics are not created equal. What are the elements that determine the robustness of a particular biometric product or technology? Here’s a quick overview of the performance metrics:
False acceptance rate or false match rate: This term measures the percent of invalid inputs which are incorrectly accepted as correct.
Threshold value: This setting determines the accuracy of the match.
False rejection rate: The probability that the system failed to match a correct try to a matching template in the database.
Equal error rate: The rate at which both accept and reject errors are equal. In general, the device with the lowest rate is most accurate.
Failure to enroll rate: The rate at which attempts to create a template from an input is unsuccessful. This is most commonly caused by low quality inputs; example, slight fingerprints.
Failure to capture rate: Within automatic systems, the probability that the system fails to detect a biometric input when presented correctly.
Speed of recognition: Speed is determined by the algorithm of the technology. The search method for the template record is key for speed; i.e., is the first record in the database a match or is it the last record in the database, which of course takes longer.
Minutiae point analysis: This is the most simple fingerprint comparison method and typically is combined with a second identifier, such as a PIN or card.
Pattern recognition: This is currently the most robust recognition technology utilizing modern algorithms for fingerprints and faces and it stores a larger template than the minutiae point analysis’ template.
Eigenvectors and mapping: These are two major technologies first used for face recognition, either alone or in combinations. Mapping measures the distances between points on the human face and has two very weak features: (1) recognition distance in front of the camera is the same as the enrollment distance was and (2) daily changes in ambient light prevented recognition. Eigenvectors-based face recognition technology is more robust with natural scaling, which means that the camera can recognize the face as soon as the camera can see the facial features. However, the normal daily changes in ambient light were problematic. Currently, varying versions of these technologies are in use.
If you enjoyed this article and want to receive more valuable industry content like this, click here to sign up for our FREE digital newsletters!
Leading in Turbulent Times: Effective Campus Public Safety Leadership for the 21st Century
This new webcast will discuss how campus public safety leaders can effectively incorporate Clery Act, Title IX, customer service, “helicopter” parents, emergency notification, town-gown relationships, brand management, Greek Life, student recruitment, faculty, and more into their roles and develop the necessary skills to successfully lead their departments. Register today to attend this free webcast!