Technical Report CIS-2005-02

Title: Surface Dependent Representations for Illumination Insensitive Image Comparison
Authors: Margarita Osadchy, David W. Jacobs, Michael Lindenbaum
Abstract: We consider the problem of matching images to tell whether they come from the same scene viewed under different lighting conditions. We show that the roughness of a surface determines the type of image comparison method that should be used. Previous work has shown the effectiveness of comparison of the direction of the gradient for rough surfaces. We show analytically that two other widely used methods, normalized correlation and comparison of multiscale oriented filters, can essentially compute the same thing. Then we show that for smooth surfaces, comparison of the output of whitening filters is most effective. This suggests that comparison of general objects should employ a combination of these strategies. We discuss indications that Gabor jets use such a mixed strategy effectively, and propose a new mixed strategy. We validate our results using both synthetic and real images.
CopyrightThe above paper is copyright by the Technion, Author(s), or others. Please contact the author(s) for more information

Remark: Any link to this technical report should be to this page (, rather than to the URL of the PDF or PS files directly. The latter URLs may change without notice.

To the list of the CIS technical reports of 2005
To the main CS technical reports page

Computer science department, Technion