Nine points of light: acquiring subspaces for face recognition under variable lighting

Previous work has demonstrated that the image variations of many objects (human faces in particular) under variable lighting can be effectively modeled by low dimensional linear spaces. Basis images spanning this space are usually obtained in one of two ways: A large number of images of the object under different conditions is acquired, and principal component analysis (PCA) is used to estimate a subspace. Alternatively, a 3D model (perhaps reconstructed from images) is used to render virtual images under either point sources from which a subspace is derived using PCA or more recently under diffuse synthetic lighting based on spherical harmonics. In this paper we show that there exists a configuration of nine point light source directions such that by taking nine images of each individual under these single sources, the resulting subspace is effective at recognition under a wide range of lighting conditions. Since the subspace is generated directly from real images, potentially complex intermediate steps such as PCA and 3D reconstruction can be completely avoided; nor is it necessary to acquire large numbers of training images or physically construct complex diffuse (harmonic) light fields. We provide both theoretical and empirical results to explain why these linear spaces should be good for recognition.