In Search of Illumination Invariants

We consider the problem of determining functions of an image of an object that are insensitive to illumination changes. We rst show that for an object with Lambertian r e e ctanc e there are no discriminative functions that are invariant to illumination. This result leads us to adopt a probabilistic appr oachin which we analytically determine a probability distribution for the image gradient as a function of the surfac e'sgeometry and re e ctanc e.Our distribution reveals that the direction of the image gradient is insensitive to changes in illumination direction. We verify this empirically by constructing a distribution for the image gradient from more than 20 million samples of gradients in a datab aseof 1,280 images of 20 inanimate objects taken under varying lighting condition. Using this distribution, we develop an illumination insensitive measur e of image comparison and test it on the problem of face recognition.

• Type: Conference
• Year: 2000
• Where: CVPR
• Authors: Hansen F. Chen, Peter N. Belhumeur, David W. Jacobs
• Keywords: Computer Vision, CVPR 2000, Illumination Changes, Illumination Direction, Illumination Insensitive Measur, Image Comparison, Image Gradient