Discriminative feature extraction and selection applied to face recognition

We propose an integrated approach to feature and architecture optimization for convolutional connectionist models. The goal is to select single features which are likely to have good discriminatory power and extract nonlinear combinations of features with the same aim. In particular, the focus is on the interaction of the feature extraction and selection modules with the recognizer design. We propose a pruning-based method called εHVS (extended HVS), where the use of a priori knowledge is adaptively optimized during a discrimination training criterion aiming at minimum classification error. Results demonstrate the selection approach´s effectiveness in identifying reduced architectures with the same recognition accuracy