Face Recognition Performance Analysis: Impact of number of training samples and trade-off between number of individuals and images per individual - temporarily withdrawn because of submission to BTAS 2015
Nicola Zanetti, Atul Kumar, Le Van Huynh, Claudia Nicolini Teixidor · University of Twente Students Journal of Biometrics and Computer Vision · 2015
We present a performance analysis of face recognition by showing the impact on a recognition performance of the number of training samples and trade-off between the number of individuals and images per individual. We investigate how the recognition performance depends on factors such as the number of individuals in the training set or the number of training images per individual. We will do that by using a face recognition system based on PCA and LDA.