This is the list of publications of this laboratory
2007
Journal Articles
Castelan, Mario; Smith, William A P; Hancock, Edwin R
A Coupled Statistical Model for Face Shape Recovery From Brightness Images Journal Article
In: IEEE Transactions on Image Processing, vol. 16, no. 4, pp. 1139-1151, 2007, ISSN: 1057-7149.
@article{4130415,
title = {A Coupled Statistical Model for Face Shape Recovery From Brightness Images},
author = {Castelan, Mario and Smith, William A P and Hancock, Edwin R },
url = {http://ieeexplore.ieee.org/document/4130415/?arnumber=4130415},
doi = {10.1109/TIP.2006.891351},
issn = {1057-7149},
year = {2007},
date = {2007-04-01},
journal = {IEEE Transactions on Image Processing},
volume = {16},
number = {4},
pages = {1139-1151},
abstract = {We focus on the problem of developing a coupled statistical model that can be used to recover facial shape from brightness images of faces. We study three alternative representations for facial shape. These are the surface height function, the surface gradient, and a Fourier basis representation. We jointly capture variations in intensity and the surface shape representations using a coupled statistical model. The model is constructed by performing principal components analysis on sets of parameters describing the contents of the intensity images and the facial shape representations. By fitting the coupled model to intensity data, facial shape is implicitly recovered from the shape parameters. Experiments show that the coupled model is able to generate accurate shape from out-of-training-sample intensity images},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
We focus on the problem of developing a coupled statistical model that can be used to recover facial shape from brightness images of faces. We study three alternative representations for facial shape. These are the surface height function, the surface gradient, and a Fourier basis representation. We jointly capture variations in intensity and the surface shape representations using a coupled statistical model. The model is constructed by performing principal components analysis on sets of parameters describing the contents of the intensity images and the facial shape representations. By fitting the coupled model to intensity data, facial shape is implicitly recovered from the shape parameters. Experiments show that the coupled model is able to generate accurate shape from out-of-training-sample intensity images