From Few to many: Illumination cone models for face recognition under variable lighting and pose

From Few to many: Illumination cone models for face recognition under variable lighting and pose (2001)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Athinodoros S. Georghiades , Peter N. Belhumeur , David J. Kriegman

Venue:	IEEE Transactions on Pattern Analysis and Machine Intelligence
Citations:	283 - 10 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	From Few to many: Illumination cone models for face recognition under variable lighting and pose	INFERENCE
AUTHOR NAME	Athinodoros S. Georghiades	SVM HeaderParse 0.2
AUTHOR AFFIL	Departments of Electrical Engineering; and Computer Science; Yale University	SVM HeaderParse 0.2
AUTHOR ADDR	New Haven, CT 06520-8285	SVM HeaderParse 0.2
AUTHOR NAME	Peter N. Belhumeur	SVM HeaderParse 0.2
AUTHOR AFFIL	Departments of Electrical Engineering; and Computer Science; Yale University	SVM HeaderParse 0.2
AUTHOR ADDR	New Haven, CT 06520-8285	SVM HeaderParse 0.2
AUTHOR NAME	David J. Kriegman	SVM HeaderParse 0.2
AUTHOR AFFIL	Beckman Institute; University of Illinois, Urbana-Champaign	SVM HeaderParse 0.2
AUTHOR ADDR	Urbana, IL 61801	SVM HeaderParse 0.2
ABSTRACT	We present a generative appearance-based method for recognizing human faces under variation in lighting and viewpoint. Our method exploits the fact that the set of images of an object in fixed pose, but under all possible illumination conditions, is a convex cone in the space of images. Using a small number of training images of each face taken with different lighting directions, the shape and albedo of the face can be reconstructed. In turn, this reconstruction serves as a generative model that can be used to render—or synthesize—images of the face under novel poses and illumination conditions. The pose space is then sampled, and for each pose the corresponding illumination cone is approximated by a low-dimensional linear subspace whose basis vectors are estimated using the generative model. Our recognition algorithm assigns to a test image the identity of the closest approximated illumination cone (based on Euclidean distance within the image space). We test our face recognition method on 4050 images from the Yale Face Database B; these images contain 405 viewing conditions (9 poses ¢ 45 illumination conditions) for 10 individuals. The method performs almost without error, except on the most extreme lighting directions, and significantly outperforms popular recognition methods that do not use a generative model.	SVM HeaderParse 0.2
YEAR	2001	INFERENCE
VENUE	IEEE Transactions on Pattern Analysis and Machine Intelligence	INFERENCE
VENUE TYPE	JOURNAL	INFERENCE
PAGES	643--660	INFERENCE
VOLUME	23	INFERENCE
CITATIONS	76 found	ParsCit 1.0