Biometric Performance as a Function of Gallery Size
Multidisciplinary Digital Publishing Institute
Many developers of biometric systems start with modest samples before general deployment. But they are interested in how their systems will work with much larger samples. To assist them, we evaluated the effect of gallery size on biometric performance. Identification rates describe the performance of biometric identification, whereas ROC-based measures describe the performance of biometric authentication (verification). Therefore, we examined how increases in gallery size affected identification rates (i.e., Rank-1 Identification Rate, or Rank-1 IR) and ROC-based measures such as equal error rate (EER). We studied these phenomena with synthetic data as well as real data from a face recognition study. It is well known that the Rank-1 IR declines with increasing gallery size. We have provided further insight into this decline. We have shown that this relationship is linear in log(Gallery Size). We have also shown that this decline can be counteracted with the inclusion of additional information (features) for larger gallery sizes. We have also described the curves which can be used to predict how much additional information is required to stabilize the Rank-1 IR as a function of gallery size. These equations are also linear in log(gallery size). We have also shown that the entire ROC curve is not systematically affected by gallery size, and so ROC-based scalar performance metrics such as EER are also stable across gallery size. Unsurpringingly, as additional uncorrelated features are added to the model, EER decreases. We were interested in exploring what changes in similarity score distributions might accompany these declines in EERs. For this, we evaluated the effect of number of features and gallery size on key distribution characteristics (median and IQR) of the genuine and impostor similarity score distributions. We present evidence that these decreases in EER are driven primarily by decreases in the spread of the impostor similarity score distribution.
Supplemental .zip file contains code for determining the ROC curve for very large datasets.
permanence, biometric analysis, synthetic data sets, Computer Science