Computer Vision Talks at Columbia University

Recognizing Objects when the Lighting Changes

David Jacobs

NEC Research Inst., Princeton, NJ 

Tuesday, May/1, 11AM 

Interschool Lab, 7th floor, CEPSR 

Host: Prof. Shree Nayar 

Abstract 

Variations in lighting can have a significant impact on the appearance of an object. In this talk I will discuss a novel characterization of this variability for the case of Lambertian (non-shiny) objects. First, we represent lighting using spherical harmonics, and describe the effects of Lambertian materials as the analog of a convolution; this is similar to working in the frequency domain in signal processing. We are then able to show that almost all the appearance of Lambertian objects is determined by the first nine components of the lighting when represented as spherical harmonics. We can therefore prove that all reflectance functions (the mapping from surface normal to intensity) produced by Lambertian objects lie close to a 9D linear subspace, explaining prior empirical results. We also provide a simple analytic characterization of the linear space of images an object can produce. This can be readily used to build efficient object recognition algorithms. We apply these ideas to face recognition, and describe experiments on a data base of 42 3-D models of faces, with 300 query images. 

* Joint work with Ronen Basri