loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR '03) - Volume 2
Low-Dimensional Representations of Shaded Surfaces under Varying Illumination
Madison, Wisconsin
June 18-June 20
ISBN: 0-7695-1900-8
ASCII Text
x 
 
Peter Nillius, Jan-Olof Eklundh, "Low-Dimensional Representations of Shaded Surfaces under Varying Illumination," Computer Vision and Pattern Recognition, IEEE Computer Society Conference on, vol. 2, pp. 185, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR '03) - Volume 2, 2003.
 
 
BibTex
x
 
@article{ 10.1109/CVPR.2003.1211469,
author = {Peter Nillius and Jan-Olof Eklundh},
title = {Low-Dimensional Representations of Shaded Surfaces under Varying Illumination},
journal ={Computer Vision and Pattern Recognition, IEEE Computer Society Conference on},
volume = {2},
year = {2003},
issn = {1063-6919},
pages = {185},
doi = {http://doi.ieeecomputersociety.org/10.1109/CVPR.2003.1211469},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
TI - Low-Dimensional Representations of Shaded Surfaces under Varying Illumination
SN - 1063-6919
SP
EP
A1 - Peter Nillius,
A1 - Jan-Olof Eklundh,
PY - 2003
KW - null
VL - 2
JA - Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
ER -
 
Peter Nillius, Computational Vision & Active Perception Laboratory (CVAP)
Jan-Olof Eklundh, Computational Vision & Active Perception Laboratory (CVAP)
The aim of this paper is to find the best representation for the appearance of surfaces with Lambertian reflectance under varying illumination. Previous work using principal component analysis (PCA) found the best sub-space to represent all images of an object under a varying point light source. We extend this to images from any illumination distribution. Specifically we calculate the bases for all configurations of a point plus ambient light source and two point light sources, as well as from a database of captured real world illumination. We also reformulate the optimization criterion used in PCA. The resulting basis, we believe has higher representability and is better for analysing images of shaded objects. The different bases are compared on a database of images to test the representability.
Citation:
Peter Nillius, Jan-Olof Eklundh, "Low-Dimensional Representations of Shaded Surfaces under Varying Illumination," cvpr, vol. 2, pp.185, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR '03) - Volume 2, 2003
Usage of this product signifies your acceptance of the Terms of Use.