Back to articles
Articles
Volume: 29 | Article ID: art00028
Image
Illumination and Reflectance Spectra Separation of Hyperspectral Image Data under Multiple Illumination Conditions
  DOI :  10.2352/ISSN.2470-1173.2017.18.COLOR-060  Published OnlineJanuary 2017
Abstract

Recently, a remarkably simple method was developed to solve the illumination and reflectance spectra separation problem (IRSS) based on the standard low-dimensionality assumption of reflectance. However, because this method assumes the scene is under one uniform illumination, it can not handle scene contains multiple illuminations or dominant shadows. In this paper, we address this problem by formulating the multiple illuminations and reflectance separation problem as a Conditional Random Field (CRF) optimization task over local separations. We then improve local illumination and reflectance separation by incorporating spatial information in each local patch.

Subject Areas :
Views 77
Downloads 12
 articleview.views 77
 articleview.downloads 12
  Cite this article 

Xiaochuan Chen, Mark S. Drew, Ze-Nian Li, "Illumination and Reflectance Spectra Separation of Hyperspectral Image Data under Multiple Illumination Conditionsin Proc. IS&T Int’l. Symp. on Electronic Imaging: Color Imaging XXII: Displaying, Processing, Hardcopy, and Applications,  2017,  pp 194 - 199,  https://doi.org/10.2352/ISSN.2470-1173.2017.18.COLOR-060

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2017
72010604
Electronic Imaging
2470-1173
Society for Imaging Science and Technology