| Authors |
Dong Huang, Storer Markus, Fernando De la Torre, Bischof Horst |
| Appeared in |
Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) |
| Date |
2011 |
| Abstract |
Head pose estimation from images has recently attracted
much attention in computer vision due to its diverse applications
in face recognition, driver monitoring and human
computer interaction. Most successful approaches to head
pose estimation formulate the problem as a nonlinear regression
between image features and continuous 3D angles
(i.e. yaw, pitch and roll). However, regression-like methods
suffer from three main drawbacks: (1) They typically
lack generalization and overfit when trained using a few
samples. (2) They fail to get reliable estimates over some
regions of the output space (angles) when the training set
is not uniformly sampled. For instance, if the training data
contains under-sampled areas for some angles. (3) They are
not robust to image noise or occlusion. To address these
problems, this paper presents Supervised Local Subspace
Learning (SL2), a method that learns a local linear model
from a sparse and non-uniformly sampled training set. SL2
learns a mixture of local tangent spaces that is robust to
under-sampled regions, and due to its regularization properties
it is also robust to over-fitting. Moreover, because
SL2 is a generative model, it can deal with image noise.
Experimental results on the CMU Multi-PIE and BU-3DFE
database show the effectiveness of our approach in terms of
accuracy and computational complexity. |
| Link |
"PDF":http://www.icg.tugraz.at/publications/pdf/storer2011_supervisedlocalsubspacelearning |
