Statistical Performance Evaluation of Biometric Authentication Systems Using Random Effects Models

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 29; no. 4; pp. 517 - 530
• Main Authors: Mitra, S., Savvides, M., Brockwell, A.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.04.2007; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Airports; Algorithms; Artificial Intelligence; Authentication; Bayesian methods; Biometrics; Biometry - methods; Computer Simulation; Data Interpretation, Statistical; Error analysis; face; Face - anatomy & histology; Fingerprint recognition; Humans; Image Interpretation, Computer-Assisted - methods; Inference; Mathematical models; Models, Biological; Models, Statistical; Pattern Recognition, Automated - methods; Performance evaluation; Permissible error; Predictive models; random effects model; Reproducibility of Results; Sensitivity and Specificity; Statistical analysis; Statistical methods; Studies; Testing; watch-list
• ISSN: 0162-8828; 2160-9292; 1939-3539
• DOI: 10.1109/TPAMI.2007.1000

As biometric authentication systems become more prevalent, it is becoming increasingly important to evaluate their performance. This paper introduces a novel statistical method of performance evaluation for these systems. Given a database of authentication results from an existing system, the method uses a hierarchical random effects model, along with Bayesian inference techniques yielding posterior predictive distributions, to predict performance in terms of error rates using various explanatory variables. By incorporating explanatory variables as well as random effects, the method allows for prediction of error rates when the authentication system is applied to potentially larger and/or different groups of subjects than those originally documented in the database. We also extend the model to allow for prediction of the probability of a false alarm on a "watch-list" as a function of the list size. We consider application of our methodology to three different face authentication systems: a filter-based system, a Gaussian mixture model (GMM)-based system, and a system based on frequency domain representation of facial asymmetry