A novel convergence acheme for active appearance models

Authors:
Aziz Umit Batur;Monson H. Hayes
Affiliations:
School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA;School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA
Venue:
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Year:
2003

Citing 7
Cited 3

From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose

IEEE Transactions on Pattern Analysis and Machine Intelligence
Active Appearance Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Recognition Using Active Appearance Models

ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
Active Appearance Models

ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
Interpreting Face Images Using Active Appearance Models

FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
The CMU Pose, Illumination, and Expression (PIE) Database

FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition
Using the Active Appearance Algorithm for Face and Facial Feature Tracking

RATFG-RTS '01 Proceedings of the IEEE ICCV Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems (RATFG-RTS'01)

Multi-View Face Alignment Using 3D Shape Model for View Estimation

ICB '09 Proceedings of the Third International Conference on Advances in Biometrics
A review of active appearance models

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Nonlinear dynamic shape and appearance models for facial motion tracking

PSIVT'07 Proceedings of the 2nd Pacific Rim conference on Advances in image and video technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

The Active Appearance Model (AAM) algorithm is a powerful tool for modeling images of deformable objects. AAM combines a subspace-based deformable model of an object's appearance with afast and robust method offitting this model to a previously unseen image. The speed of this algorithm comesfrom the assumption that the gradient matrix isfixed around the optimal coefficientsforall images. In this paper, we propose a novel convergence scheme for AAM that adapts this gradient matrix to the target image's texture during convergence by adding linear modes of change that are based on the texture eigenvectors of AAM. We show that this adaptive strategy for the gradient matrix provides a significant increase in the performance of the AAM algorithm.