Keystroke Biometric: Receiver Operating Characteristics (ROC) Experiments
Robert S. Zack, Abhishek Kanchan, Priyanka Ranadive, Sagar Desai, Pooja Mahotra, Ning Wang, Charles C. Tappert · 2010
In biometric authentication systems the Receiver Operating Characteristic (ROC) curve is a graphical representation of the trade-off between the False Accept Rate (FAR) and the False Reject Rate (FRR). The ROC curve is important in describing the performance of a biometric authentication system. It helps to determine where to set the operating point. The k-Nearest-Neighbor (kNN) pattern recognition procedure is a nonparametric method of classifying patterns based on the nearest training samples in feature space and is used in the experiments described in the following sections. While the derivation of ROC curves from parametric classification procedures is well understood, little is known about obtaining ROC curves from the kNN classification procedure. A vector-difference model and data from a keystroke biometric authentication system are explored in these ROC experiments.