The Active Wavelet Network (AWN) [9] approach was recently proposed for automatic face alignment, showing advantages over Active Appearance Models (AAM), such as more robustness against partial occlusions and illumination changes. In this paper, we (1) extend the AWN method to a view-based approach, (2) verify the robustness of our algorithm with respect to unseen views in a large dataset and (3) show that using only nine wavelets, our method yields similar performance 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 a 1.6GHz Pentium IV. We show applications in face alignment for recognition and real-time facial feature tracking under large pose variations.