This paper addresses the problem of predicting recognition performance on a large population from a small gallery. Unlike the current approaches based on a binominal model that use match and non-match scores, this paper presents a generalized two-dimensional model that integrates a hypogeometric probabilty distribution model explicity with a binominal model. The distortion caused by sensor noise, feature uncertainty, feature occlusion and feature clutter in the gallery data is modeled. The prediction model provides performance measures as a function of rank, population size and the number of distorted images. Results are shown on NIST-4 fingerprint database and 3D ear database for various sizes of gallery and the population.
Mendeley saves you time finding and organizing research
Choose a citation style from the tabs below