Statistical transformations of frontal models for non-frontal face verification

In the framework of a face verification system using local features and a Gaussian mixture model based classifier, we address the problem of non-frontal face verification (when only a single (frontal) training image is available) by extending each client\´s frontal face model with artificially synthesized models for non-frontal views. Furthermore, we propose the maximum likelihood shift (MLS) synthesis technique and compare its performance against a maximum likelihood linear regression (MLLR) based technique (originally developed for adapting speech recognition systems) and the recently proposed "difference between two universal background models" (UBMdiff) technique. All techniques rely on prior information and learn how a generic face model for the frontal view is related to generic models at non-frontal views. Experiments on the FERET database suggest that that the proposed MLS technique is more suitable than MLLR (due to a lower number of free parameters) and UBMdiff (due to lack of heuristics). The results further suggest that extending frontal models considerably reduces errors.