publication . Other literature type . Article . 2001

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

David J. Kriegman; Athinodoros S. Georghiades; Peter N. Belhumeur;
Open Access
  • Published: 01 Jun 2001
  • Publisher: (:unav)
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 correspond...
ACM Computing Classification System: ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONComputingMethodologies_COMPUTERGRAPHICS
free text keywords: Computational Theory and Mathematics, Software, Applied Mathematics, Artificial Intelligence, Computer Vision and Pattern Recognition, Generative model, Convex cone, Basis (linear algebra), Illumination problem, Computer vision, Iterative reconstruction, Standard test image, Image-based modeling and rendering, Computer science, Facial recognition system, business.industry, business
Any information missing or wrong?Report an Issue