On Evaluating Open Biometric Identification Systems
Michael C. Gibbons, Sungsoo Yoon, Sung-Hyuk Cha, Charles C. Tappert · 2005
This paper concerns the generalizability of biometric identification in open systems. Many researchers have claimed high identification accuracies on closed system consisting of a few hundred or thousand members. Here, we consider what happens to these closed identification systems as they are opened to non-members. We claim that these systems do not generalize well as the non-member population increases. To support this claim, we first take a look at the visualization of pattern classification using Support Vector Machines (SVM), Nearest Neighbor (NN) and Artificial Neural Network (ANN). Next, we present experimental results on writer and iris biometric databases using the afore mentioned classifiers. We find that system security (1-FAR) decreases rapidly for closed systems when they are tested in open-system mode as the number of non members tested increases. We also find that, although systems can be trained for greater closed-system security using SVM rather than NN classifiers, the NN classifiers are better for generalizing to open systems due to their superior capability of rejecting non members.