In Search of Illumination Invariants

Abstract

We consider the problem of determining functions of an image of an object that are insensitive to illumination changes. We first show that for an object with Lambertian reflectance there are no discriminative functions that are invariant to illumination. We do this by showing that given any two images, one can construct a single Lambertian object that can produce both images under two very simple lighting conditions. This result leads us to adopt a probabilistic approach in which we analytically determine a probability distribution for the image gradient as a function of the surface's geometry and reflectance. 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 database of1,280 images of 20 inanimate objects taken under varying lighting conditions. Using this distribution, we develop an illumination insensitive measure of image comparison and test it on the problem of face recognition.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2000
Accession Number
AD1015513

Entities

People

  • David W. Jacobs
  • Hansen F. Chen
  • Peter N. Belhumeur

Organizations

  • Yale University

Tags

Communities of Interest

  • Air Platforms

DTIC Thesaurus Topics

  • Computational Science
  • Computer Vision
  • Coordinate Systems
  • Databases
  • Geometry
  • Integral Equations
  • Intensity
  • Light Sources
  • Pattern Recognition
  • Probabilistic Models
  • Probability
  • Probability Density Functions
  • Probability Distributions
  • Random Variables
  • Recognition
  • Three Dimensional
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Regression Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms