Real-time view-based face alignment using active wavelet networks
- 23 April 2004
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
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.Keywords
This publication has 13 references indexed in Scilit:
- Multi-view face pose estimation based on supervised ISA learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Multi-view face alignment using direct appearance modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- View-based active appearance modelsImage and Vision Computing, 2002
- Active appearance modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2001
- Incremental Focus of Attention for Robust Vision-Based TrackingInternational Journal of Computer Vision, 1999
- A Comparative Evaluation of Active Appearance Model AlgorithmsPublished by British Machine Vision Association and Society for Pattern Recognition ,1998
- Face recognition by elastic bunch graph matchingIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997
- Active Shape Models-Their Training and ApplicationComputer Vision and Image Understanding, 1995
- A unified approach to boundary perception: edges, textures, and illusory contoursIEEE Transactions on Neural Networks, 1993
- Feature extraction from faces using deformable templatesInternational Journal of Computer Vision, 1992