Multi-View Face Detection (2005~2007)
Faster and more robust detection of multi-view faces under various circumstances.
A tree-structured face detector trained by Vector Boosting covers a range of +/-45 degree rotation in plane and +/-90 degree yaw extent of the face. Speed is about 10 fps on 320x240 sized images.
- Chang HUANG, Haizhou AI, Yuan LI, Shihong LAO, High Performance Rotation Invariant Multi-View Face Detection, IEEE Transactions on Pattern Analysis and Machine Intelligence,Vol.29, No.4, pp. 671-686, April 2007.
- Chang HUANG, Haizhou AI, Yuan LI, Shihong LAO, Learning Sparse Features in Granular Space for Multi-View Face Detection, 7th IEEE International Conference, Automatic Face and Gesture Recognition, FG2006 (oral paper), pp.401-406, Southampton, UK, April 10-12 2006.
- Chang HUANG, Haizhou AI, Yuan LI, Shihong LAO, Vector Boosting for Rotation Invariant Multi-View Face Detection, The IEEE International Conference on Computer Vision, ICCV-05 (oral paper), pp.446-453, Beijing, China, Oct 17-20, 2005.