To search, Click below search items.


All Published Papers Search Service


Performance Metrics for Eigen and Fisher Feature Based Face Recognition Algorithms


Harihara Santosh Dadi, Krishna Mohan P.G.


Vol. 16  No. 6  pp. 157-168


three performance curves for evaluation of face recognition algorithms are introduced in this paper. Cumulative Match Score Curves (CMC) is the curve between the rank and face recognition rate. Expected Performance Curves (EPC) is the graph between the alpha and error rate. Receiver Operating Characteristics (ROC) is the graph between false acceptance rate and verification rate. Twelve face recognition algorithms based on Eigen and fisher features are compared based on these curves. The performances of all these algorithms are analyzed based on these metrics.


Facial features, Principle Component Analysis, Kernel Fisher Analysis, Kernel Principle Component Analysis, Linear Discriminant Analysis, CMC, EPC, ROC.