From few to many: illumination cone models for face recognition under variable lighting and pose

S. Georghiades, Athinodoros; N. Belhumeur, Peter; Kriegman, David

doi:10.1109/34.927464

Public

From few to many: illumination cone models for face recognition under variable lighting and pose

Published in IEEE Transactions on Pattern Analysis and Machine Intelligence • Jun 1, 2001

Authors:

Athinodoros S. Georghiades

Peter N. Belhumeur

David Kriegman

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 smal...

View

Paywalled

Subject

Artificial intelligence

Computer vision

Computer science

Generate AI Take for this paper

Highlights, strengths & weaknesses, commercial applications, and societal impact — written for this paper on demand.

Subject

Generate AI Take for this paper

Discussions