Real-time View-based Face Alignment using Active Wavelet Networks

The Active Wavelet Network (AWN) approach was recentlyproposed for automatic face alignment, showing advantagesover Active Appearance Models (AAM), such asmore robustness against partial occlusions and illuminationchanges. In this paper, we (1) extend the AWN method to aview-based approach, (2) verify the robustness of our algorithmwith respect to unseen views in a large dataset and (3)show that using only nine wavelets, our method yields similarperformance to state-of-the-art face alignment systems,with a significant enhancement in terms of speed. After optimization,our system requires only 3ms per iteration on a1.6GHz Pentium IV.We show applications in face alignmentfor recognition and real-time facial feature tracking underlarge pose variations.