Mixtures of Boosted Classifiers for Frontal Face Detection

This paper describes a new approach to automatic frontal face detection which employs Gaussian filters as local image descriptors. We then show how the paradigm of classifier combination can be used for building a face detector that outperforms the current state--of--the--art systems, while remaining fast enough for being used in real--time systems. It is based on the combination of several parallel classifiers trained on subsets of the complete training set. We report a number of results on some reference datasets and we use an unbiased method for comparing the detectors.