- 1 January 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 1-8
Abstract
Appearance models have been applied to model the space of human faces over the last two decades. In particular, active appearance models (AAMs) have been successfully used for face tracking, synthesis and recognition, and they are one of the state-of-the-art approaches due to its efficiency and representational power. Although widely employed, AAMs suffer from a few drawbacks, such as the inability to isolate pose, identity and expression changes. This paper proposes Bilinear Active Appearance Models (BAAMs), an extension of AAMs, that effectively decouple changes due to pose and expression/identity. We derive a gradient-descent algorithm to efficiently fit BAAMs to new images. Experimental results show how BAAMs improve generalization and convergence with respect to the linear model. In addition, we illustrate decoupling benefits of BAAMs in face recognition across pose. We show how the pose normalization provided by BAAMs increase the recognition performance of commercial systems.Keywords
This publication has 29 references indexed in Scilit:
- Face transfer with multilinear modelsACM Transactions on Graphics, 2005
- Bilinear factorisation for facial expression analysis and synthesisIEE Proceedings - Vision, Image, and Signal Processing, 2005
- Active Appearance Models RevisitedInternational Journal of Computer Vision, 2004
- Automatic construction of active appearance models as an image coding problemIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Face recognitionACM Computing Surveys, 2003
- Robustly Estimating Changes in Image AppearanceComputer Vision and Image Understanding, 2000
- Probabilistic visual learning for object representationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997
- Eigenfaces for RecognitionJournal of Cognitive Neuroscience, 1991
- Low-dimensional procedure for the characterization of human facesJournal of the Optical Society of America A, 1987
- Lower Rank Approximation of Matrices by Least Squares With Any Choice of WeightsTechnometrics, 1979