Acquiring linear subspaces for face recognition under variable lighting

DMCA

Acquiring linear subspaces for face recognition under variable lighting (2005)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Kuang-chih Lee , Jeffrey Ho , David Kriegman

Venue:	IEEE Transactions on Pattern Analysis and Machine Intelligence
Citations:	317 - 2 self

BibTeX

@ARTICLE{Lee05acquiringlinear,
    author = {Kuang-chih Lee and Jeffrey Ho and David Kriegman},
    title = {Acquiring linear subspaces for face recognition under variable lighting},
    journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
    year = {2005},
    volume = {27},
    pages = {684--698}
}

OpenURL

Abstract

Previous work has demonstrated that the image variation of many objects (human faces in particular) under variable lighting can be effectively modeled by low dimensional linear spaces, even when there are multiple light sources and shadowing. Basis images spanning this space are usually obtained in one of three ways: A large set of images of the object under different lighting conditions is acquired, and principal component analysis (PCA) is used to estimate a subspace. Alternatively, synthetic images are rendered from a 3D model (perhaps reconstructed from images) under point sources, and again PCA is used to estimate a subspace. Finally, images rendered from a 3D model under diffuse lighting based on spherical harmonics are directly used as basis images. In this paper, we show how to arrange physical lighting so that the acquired images of each object can be directly used as the basis vectors of a low-dimensional linear space, and that this subspace is close to those acquired by the other methods. More specifically, there exist configurations of k point light source directions, with k typically ranging from 5 to 9, such that by taking k images of an object under these single sources, the resulting subspace is an effective representation for recognition under a wide range of lighting conditions. Since the subspace is generated directly from real images, potentially complex and/or brittle intermediate steps such as 3D reconstruction can be completely avoided; nor is it necessary to acquire large numbers of training images or to physically construct complex diffuse (harmonic) light fields. We validate the use of subspaces constructed in this fashion within the context of face recognition.

Keyphrases

variable lighting face recognition linear subspace principal component analysis training image physical lighting acquired image multiple light source intermediate step light field low-dimensional linear space different lighting condition previous work many object complex diffuse low dimensional linear space basis image spherical harmonic basis vector large set single source point source synthetic image large number point light source direction real image image variation effective representation wide range

DMCA