Extrapolating Single View Face Models for Multi-View Recognition
Open Access
- 1 January 2004
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Copyright © 2004 IEEEPerformance of face recognition systems can be adversely affected by mismatches between training and test poses, especially when there is only one training image available. We address this problem by extending each statistical frontal face model with artificially synthesized models for non-frontal views. The synthesis methods are based on several implementations of maximum likelihood linear regression (MLLR), as well as standard multivariate linear regression (LinReg). All synthesis techniques utilize prior information on how face models for the frontal view are related to face models for non-frontal views. The synthesis and extension approach is evaluated by applying it to two face verification systems: PCA based (holistic features) and DCTmod2 based (local features). Experiments on the FERET database suggest that for the PCA based system, the LinReg technique (which is based on a common relation between two sets of points) is more suited than the MLLR based techniques (which in effect are "single point to single point" transforms). For the DCTmod2 based system, the results show that synthesis via a new MLLR implementation obtains better performance than synthesis based on traditional MLLR (due to a lower number of free parameters). The results further show that extending frontal models considerably reduces errors.Conrad Sanderson and Samy BengiKeywords
This publication has 18 references indexed in Scilit:
- Authentication gets personal with biometricsIEEE Signal Processing Magazine, 2004
- Face identification across different poses and illuminations with a 3D morphable modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Face Verification Competition on the XM2VTS DatabasePublished by Springer Nature ,2003
- Comparison of MLP and GMM Classifiers for Face Verification on XM2VTSPublished by Springer Nature ,2003
- Growing Gaussian mixture models for pose invariant face recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Why recognition in a statistics-based face recognition system should be based on the pure face portion: a probabilistic decision-based proofPattern Recognition, 2001
- The FERET evaluation methodology for face-recognition algorithmsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2000
- Speaker Verification Using Adapted Gaussian Mixture ModelsDigital Signal Processing, 2000
- Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov modelsComputer Speech & Language, 1995
- View-based and modular eigenspaces for face recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994