An Introduction to Biometric-completeness: The Equivalence of Matching and Quality

Published

June 16, 2009

Author(s)

P J. Phillips, J. R. Beveridge

Abstract

This paper introduces the concept of biometric-completeness. A problem is biometric-complete if solving the problem is equivalent to solving a biometric recognition problem. The concept of biometric-completeness is modeled on the informal concept of artificial intelligence (AI) completeness. The concept of biometric-completeness is illustrated by showing a formal equivalence between biometric recognition and quality assessment of biometric samples. The model allows for the inclusion of quality of biometric samples in verification decisions. The model includes most methods for incorporating quality into biometric systems. The key result in this paper shows that finding the perfect quality measure for any algorithm is equivalent to finding the perfect verification algorithm. Two results that follow from the main result are: finding the perfect quality measure is equivalent to solving the open-set and closed-set identification problems; and that a universal perfect quality measure cannot exist.

Proceedings Title

IEEE Third International Conference on Biometrics: Theory, Applications and Systems

Conference Dates

September 28-30, 2009

Conference Location

Crystal City, VA

Pub Type

Conferences

Download Paper

Local Download

Citation

Phillips, P. and Beveridge, J. (2009), An Introduction to Biometric-completeness: The Equivalence of Matching and Quality, IEEE Third International Conference on Biometrics: Theory, Applications and Systems , Crystal City, VA, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=903122 (Accessed March 13, 2025)