The following are results of our system vs FRGC2 Baseline at 10^-3 FAR (False Accept Rate), which consists of 4007 datasets; The largest available 3D Face Database in the world.

In the FRGC three masks are defined over the square similarity matrix which holds the similarity values between facial records. Each mask is used to perform a different verification experiment, thus producing three different ROC curves, which will be referred to as ROC I,II and III. A mask selects a subset of the records to be used as the gallery set and another subset to be used as the probe set. In ROC I all the data are within semesters, in ROC II they are within a year, while in ROC III the samples are between semesters. These experiments are of increasing difficulty.