Segmented Linear Subspaces for Illumination-Robust Face Recognition

Authors:
A. U. Batur;M. H. Hayes, III
Affiliations:
Center for Signal and Image Processing, School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332;Center for Signal and Image Processing, School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332
Venue:
International Journal of Computer Vision
Year:
2004

Citing 8
Cited 1

On Photometric Issues in 3D Visual Recognition from aSingle 2D Image

International Journal of Computer Vision
Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Recognition: The Problem of Compensating for Changes in Illumination Direction

IEEE Transactions on Pattern Analysis and Machine Intelligence
What Is the Set of Images of an Object Under All Possible Illumination Conditions?

International Journal of Computer Vision
The Bas-Relief Ambiguity

International Journal of Computer Vision
From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose

IEEE Transactions on Pattern Analysis and Machine Intelligence
Analytic PCA Construction for Theoretical Analysis of Lighting Variability in Images of a Lambertian Object

IEEE Transactions on Pattern Analysis and Machine Intelligence
Illumination invariant object recognition

ICIP '95 Proceedings of the 1995 International Conference on Image Processing (Vol. 3)-Volume 3 - Volume 3

Fusion of classifiers for illumination robust face recognition

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

All images of a convex Lambertian surface captured with a fixed pose under varying illumination are known to lie in a convex cone in the image space that is called the illumination cone. Since this cone model is too complex to be built in practice, researchers have attempted to approximate it with simpler models. In this paper, we propose a segmented linear subspace model to approximate the cone. Our idea of segmentation is based on the fact that the success of low dimensional linear subspace approximations of the illumination cone increases if the directions of the surface normals get close to each other. Hence, we propose to cluster the image pixels according to their surface normal directions and to approximate the cone with a linear subspace for each of these clusters separately. We perform statistical performance evaluation experiments to compare our system to other popular systems and demonstrate that the performance increase we obtain is statistically significant.