We consider a class of region-based energies for image
segmentation and inpainting which combine region integrals
with curvature regularity of the region boundary. To
minimize s...
Subspace learning techniques are widespread in pattern recognition research. They include PCA, ICA, LPP, etc. These techniques are generally linear and unsupervised. The problem o...
This paper presents a novel approach to the problem of determining head pose estimation and face 3D orientation of several people in low resolution sequences from multiple calibra...
Cristian Canton-Ferrer, Josep R. Casas, Montse Par...
We introduce a new EM framework in which it is possible not only to optimize the model parameters but also the number of model components. A key feature of our approach is that we...
Face recognition using image-set or video sequence as input tends to be more robust since image-set or video sequence provides much more information than single snapshot about the ...