We present the methodology and recognition performance characteristics used in the Face Recognition Vendor Test 2002. We refine the notion of a biometric imposter, and show that the traditional measures of identification and verification performance are limiting case specializations of a novel watch list scenario. The watch list problem is a newly important and operationally realistic generalization of both detection and identification of persons of interest, together with simultaneous verification-like constraints on false alarm rates. In addition, we use performance scores on disjoint populations to establish a novel means of computing and displaying distribution-free estimates of the variation of verification vs. false alarm performance. Finally, we formalize gallery normalization, which is an extension of previous evaluation methodologies; we define a pair of gallery dependent mappings that can be applied as a post recognition step to vectors of distance or similarity scores. All the methods are biometric non-specific, and applicable to large populations.
Citation: NIST Interagency/Internal Report (NISTIR) - 6982Report Number:
NIST Pub Series: NIST Interagency/Internal Report (NISTIR)
Pub Type: NIST Pubs
biometrics, evaluation, face recognition, FRVT 2002