The active wavelet network (AWN) [C. Hu et al., (2003)] 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. 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 3 ms per iteration on a 1.6 GHz Pentium IV. We show applications in face alignment for recognition and real-time facial feature tracking under large pose variations.
Real-time view-based face alignment using active wavelet networks
2003-01-01
526286 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Real-Time View-Based Face Alignment Using Active Wavelet Networks
British Library Conference Proceedings | 2003
|Face Alignment Using Statistical Models and Wavelet Features
British Library Conference Proceedings | 2003
|Efficient real-time face tracking in wavelet subspace
IEEE | 2001
|Efficient Real-Time Face Tracking in Wavelet Subspace
British Library Conference Proceedings | 2001
|