Recognition by Linear Combinations of Models
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part I
Feature extraction from faces using deformable templates
International Journal of Computer Vision
Pattern theory: a unifying perspective
Perception as Bayesian inference
Linear Object Classes and Image Synthesis From a Single Example Image
IEEE Transactions on Pattern Analysis and Machine Intelligence
Recognizing Facial Expressions in Image Sequences Using Local Parameterized Models of Image Motion
International Journal of Computer Vision
Analysis and Synthesis of Facial Image Sequences Using Physical and Anatomical Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Contour Tracking by Stochastic Propagation of Conditional Density
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
Learning-Based Approach to Real Time Tracking and Analysis of Faces
FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
Example Based Image Analysis and Synthesis
Example Based Image Analysis and Synthesis
Model-Based Matching by Linear Combinations of Prototypes
Model-Based Matching by Linear Combinations of Prototypes
Visual Speech Synthesis by Morphing Visemes
Visual Speech Synthesis by Morphing Visemes
Multidimensional Morphable Models
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
| Hi-index | 0.01 |
This paper describes a method for estimating the parameters of a linear morphable model (LMM) that models mouth images. The method uses a supervised learning approach based on support vector machines (SVM) to estimate the LMM parameters directly from pixel-based representations of images of the object class (in this case mouths). This method can be used to bypass or speed up current computationally intensive methods that implement analysis by synthesis, for matching objects to morphable models. We show that the principal component axes of the flow space of the LMM correspond to easily discernible expressions such as openness, smile and pout. Therefore our method can be used to estimate the degrees of these expressions in a supervised learning framework without the need for manual annotation of a training set. We apply this to drive a cartoon character from the video of a persons face.