On transforming statistical models for non-frontal face verification

Sanderson, Conrad, Bengio, Samy and Gao, Yongsheng (2006) On transforming statistical models for non-frontal face verification. Pattern Recognition, 39 2: 288-302. doi:10.1016/j.patcog.2005.07.001

Author Sanderson, Conrad
Bengio, Samy
Gao, Yongsheng
Title On transforming statistical models for non-frontal face verification
Journal name Pattern Recognition   Check publisher's open access policy
ISSN 0031-3203
Publication date 2006-02-01
Sub-type Article (original research)
DOI 10.1016/j.patcog.2005.07.001
Open Access Status Not Open Access
Volume 39
Issue 2
Start page 288
End page 302
Total pages 15
Editor F. J. Ferri
J. Salvador Sanchez
F. Pla
Place of publication Amsterdam: North-Holland
Publisher Elsevier B.V.
Language eng
Subject 080104 Computer Vision
080109 Pattern Recognition and Data Mining
080106 Image Processing
010401 Applied Statistics
Abstract We address the pose mismatch problem which can occur in face verification systems that have only a single (frontal) face image available for training. In the framework of a Bayesian classifier based on mixtures of gaussians, the problem is tackled through extending each 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 multi-variate linear regression (LinReg). All synthesis techniques rely on prior information and learn 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: a holistic system (based on PCA-derived features) and a local feature system (based on DCT-derived features). Experiments on the FERET database suggest that for the holistic system, the LinReg-based technique is more suited than the MLLR-based techniques; for the local feature system, the results show that synthesis via a new MLLR implementation obtains better performance than synthesis based on traditional MLLR. The results further suggest that extending frontal models considerably reduces errors. It is also shown that the local feature system is less affected by view changes than the holistic system; this can be attributed to the parts based representation of the face, and, due to the classifier based on mixtures of gaussians, the lack of constraints on spatial relations between the face parts, allowing for deformations and movements of face areas.
Keyword Biometrics
Pose mismatch;
Face recognition
Local features
Gaussian mixture model
Prior information
Model synthesis
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status Unknown

Document type: Journal Article
Sub-type: Article (original research)
Collection: School of Information Technology and Electrical Engineering Publications
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 32 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 41 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Wed, 01 Apr 2009, 20:21:06 EST by Laura McTaggart on behalf of School of Information Technol and Elec Engineering