Predicting Face Recognition Performance in Unconstrained Environments

While face recognition algorithms perform under many different unconstrained conditions, predicting this performance is not possible when a new location is introduced. Analyzing the impostor distribution of the videos of the Point-and-Shoot Challenge (PaSC) as well as its relationship to the genuine match distribution, we show that there is large variation in the false accept rate over the impostor distribution, demonstrate there is a correlation between changes in the verification and false accept rates over factor, and using this, present a method for predicting the performance of an algorithm using only unlabeled data for a new location.