Comparing images under variable illumination
- 27 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 610-617
- https://doi.org/10.1109/cvpr.1998.698668
Abstract
We consider the problem of determining whether two images come from different objects or the same object in the same pose, but under different illumination conditions. We show that this problem cannot be solved using hard constraints: even using a Lambertian reflectance model, there is always an object and a pair of lighting conditions consistent with any two images. Nevertheless, we show that for point sources and objects with Lambertian reflectance, the ratio of two images from the same object is simpler than the ratio of images from different objects. We also show that the ratio of the two images provides two of the three distinct values in the Hessian matrix of the object's surface. Using these observations, we develop a simple measure for matching images under variable illumination, comparing its performance to other existing methods on a database of 450 images of 10 individuals.Keywords
This publication has 23 references indexed in Scilit:
- Illumination cones for recognition under variable lighting: facesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Surface Curvature and Shape Reconstruction from Unknown Multiple Illumination and IntegrabilityComputer Vision and Image Understanding, 1997
- What is the set of images of an object under all possible lighting conditions?Published by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- The generic viewpoint assumption in a framework for visual perceptionNature, 1994
- A low-dimensional representation of human faces for arbitrary lighting conditionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994
- A novel algorithm for color constancyInternational Journal of Computer Vision, 1990
- Application of the Karhunen-Loeve procedure for the characterization of human facesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Aligning pictorial descriptions: An approach to object recognitionCognition, 1989
- Perceptual Organization and Visual RecognitionPublished by Springer Nature ,1985
- Determining lightness from an imageComputer Graphics and Image Processing, 1974