Independent Component Analysis of Face Images

Authors:
Pong C. Yuen;Jian-Huang Lai
Affiliations:
-;-
Venue:
BMVC '00 Proceedings of the First IEEE International Workshop on Biologically Motivated Computer Vision
Year:
2000

Citing 5
Cited 1

Fundamentals of matrix computations

Fundamentals of matrix computations
Independent component analysis, a new concept?

Signal Processing - Special issue on higher order statistics
Adaptive blind separation of independent sources: a deflation approach

Signal Processing
Eigenfaces for recognition

Journal of Cognitive Neuroscience
Fast and robust fixed-point algorithms for independent component analysis

IEEE Transactions on Neural Networks

A survey on feature extraction for pattern recognition

Artificial Intelligence Review

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper addresses the problem of face recognition using independent component analysis. As the independent components (IC) are not orthogonal, to represent a face image using the determined ICs, the ICs have to be orthogonalized, where two methods, namely Gram-Schmit Method and Householder Transformation, are proposed. In addition, to find a better set of ICs for face recognition, an efficient IC selection algorithm is developed. Face images with different facial expressions, pose variations and small occlusions are selected to test the ICA face representation and the results are encouraging.