Menu
Close
Close
Data science

Biometrics

Evaluating the performance of biometric systems

Biometric identification technologies, such as automatic face, fingerprint and iris recognition, are used for user authentication in a variety of applications including computer login, building access control and fast-track clearance through immigration. Current proposals for national identity cards also consider using of biometrics to help in preventing identity fraud.

Biometric technologies measure a variety of anatomical, physiological and behavioural characteristics, and use the measurements to distinguish between different people. They can check that the image or signal presented is that of a real face, fingerprint, hand profile or iris, rather than that of a fake.

We develop and improve methodologies for evaluating the performance of biometric systems, conducting evaluations and technical consultancy on biometric system performance. Measurements of a living entity vary from one occasion to the next, and are highly dependent on environmental conditions and user behaviour. We develop reliable international comparison of biometric techniques to lead to more robust and accurate recognition.

Lead researcher

Tony Mansfield

Principal Research Scientist

Dr Tony Mansfield studied mathematics at the University of Oxford, and joined NPL on completion of his DPhil in 1982. At NPL, he has worked on a variety of projects, including development of tools for performance evaluation of parallel systems, and validation of neural networks and other AI methods.

View Tony's profile

Work with us

Our research and measurement solutions support innovation and product development. We work with companies to deliver business advantage and commercial success.
Contact our Customer Services team on +44 20 8943 7070