Image and Vision Computing - Special issue: frequency increase for 1991
Boundary Finding with Parametrically Deformable Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Feature extraction from faces using deformable templates
International Journal of Computer Vision
A morphable model for the synthesis of 3D faces
Proceedings of the 26th annual conference on Computer graphics and interactive techniques
IEEE Transactions on Pattern Analysis and Machine Intelligence
Detecting Faces in Images: A Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
Tracking Facial Features Using Probabilistic Network
FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
Learning to Identify and Track Faces in Image Sequences
FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
An active model for facial feature tracking
EURASIP Journal on Applied Signal Processing
Model-based real-time head tracking
EURASIP Journal on Applied Signal Processing
Journal of Cognitive Neuroscience
Fast Active Appearance Model Search Using Canonical Correlation Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Facial motion cloning with radial basis functions in MPEG-4 FBA
Graphical Models
Computer Vision and Image Understanding
Hi-index | 0.00 |
This paper addresses the 3D tracking of pose and animation of thehuman face in monocular image sequences using Active AppearanceModels. The classical appearance-based tracking suffers from twodisadvantages: (i) the estimated out-of-plane motions are not veryaccurate, and (ii)the convergence of the optimization process todesired minima is not guaranteed. In this paper, we aim atdesigning an efficient active appearance model which is able tocope with the above disadvantages by retaining the strengthsoffeature-based and featureless tracking methodologies. For eachframe, the adaptation is split into two consecutive stages. In thefirst stage, the 3D head pose is recovered using robust statisticsand a measure of consistency with a statistical model of a facetexture. In the second stage, the local motion associated with somefacial features is recovered using the concept of the activeappearance model search. Tracking experiments and method comparisondemonstrate the robustness and out-performance of the developedframework.