Recovering Facial Shape Using a Statistical Model of Surface Normal Direction
IEEE Transactions on Pattern Analysis and Machine Intelligence
Weighted principal geodesic analysis for facial gender classification
CIARP'07 Proceedings of the Congress on pattern recognition 12th Iberoamerican conference on Progress in pattern recognition, image analysis and applications
Graph embedding using commute time
SSPR'06/SPR'06 Proceedings of the 2006 joint IAPR international conference on Structural, Syntactic, and Statistical Pattern Recognition
Manifold embedding of graphs using the heat kernel
IMA'05 Proceedings of the 11th IMA international conference on Mathematics of Surfaces
| Hi-index | 0.00 |
This paper explores whether facial expressions can be recognised by using the distribution of surface normal directions in the extended Gaussian image (EGI). We work with range images and extract surface normals using a mesh fitting technique. Our representation of the surface normals is based on the co-efficients of spherical harmonics extracted from the EGI. We explore whether the co-efficients can be used to construct shape-spaces that capture variations in facial expression using a number of manifold learning techniques. Based on a comparison of various alternatives, the best results are given by the diffusion map.