Classification of Facial Images Using Gaussian Mixture Models

Authors:
Pin Liao;Wen Gao;Li Shen;Xilin Chen;Shiguang Shan;Wenbing Zeng
Affiliations:
-;-;-;-;-;-
Venue:
PCM '01 Proceedings of the Second IEEE Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Year:
2001

Citing 4
Cited 1

Support vector machines applied to face recognition

Proceedings of the 1998 conference on Advances in neural information processing systems II
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Probabilistic visual learning for object detection

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Eigenfaces for recognition

Journal of Cognitive Neuroscience

So near and yet so far: New insight into properties of some well-known classifier paradigms

Information Sciences: an International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a new technique for face recognition. Two distinct and mutually exclusive classes of difference between two facial images are defined: within-class differences set (differences in appearance of the same individual) and between-class differences set (differences in appearance between different individuals). Then Gaussian mixture models (GMMs) are used to estimate the eigenspace densities of the two classes. And subsequently a matching similarity measure is computed based on the maximum likelihood (ML) method. The new method achieved as much as 45% error reduction compared to the standard eigenface approach on the ORL database.