IPLS

************************************************************
* author: Emilie Chouzenoux       		           *
* institution: LIGM - Universite de Marne la Vallee / CNRS *
* (joint work with S. Moussaoui, M. Legendre and J. Idier  *
*       IRCCyN - Ecole Centrale de Nantes / CNRS)          *
* date: Friday, October 11st 2013   	                   *
* License CeCILL-B                                         *
************************************************************


*****************************************************
* RECOMMENDATIONS:                                  *
* This toolbox is designed to work with             *
* Matlab 7.0                                        *
*****************************************************


---------------------------------------------------------------------------
DESCRIPTION:
This toolbox allows to solve the linear unmixing problem encountered in 
hyperspectral imagery. Given an noisy observation data matrix Y \in R^{LxN}, 
and P endmember spectra concatenated into a matrix S \in R^{LxP}, the IPLS 
(Interior Point Least Squares) algorithm solves:

        min_{A\in R^{PxN}} F(A) = || Y - A S ||^2_F, 

where ||.||_F denotes the Frobenius norm, under one of the following constraints:

(POS) A >=0
(STO) A >=0 and sum(A(:,n)) = 1 for all n
(SLO) A >=0 and sum(A(:,n)) <= 1 for all n

The optimization process is based on a primal-dual interior point approach.

The toolbox consists of 2 subfolders:
1)  data : contains reflectance spectra from the USGS (U.S. Geological Survey)
spectral library
2)  include : contains the IPLS algorithm.

--------------------------------------------------------------------------- 
SPECIFICATIONS for using IPLS:

The demo file demounmixing.m running an spectral unmixing example is provided. 
 
---------------------------------------------------------------------------
RELATED PUBLICATIONS:

#   E. Chouzenoux, M. Legendre, S. Moussaoui and J. Idier. "Fast Constrained 
Least Squares Spectral Unmixing using Primal-Dual Interior Point Optimization,"
IEEE Journal of Selected Topics in Applied Earth Observations 
and Remote Sensing, to appear, 2013. 

# E. Chouzenoux, S. Moussaoui, M. Legendre and J. Idier. "Algorithme primal-
dual de points intrieurs pour lestimation pnalise des cartes dabondances 
en imagerie hyperspectrale," Traitement du Signal, Vol. 30, No. 1-2, pages 
35-59, 2013.

# S. Moussaoui, E. Chouzenoux and J. Idier. "Primal-Dual Interior Point 
Optimization for Penalized Least Squares Estimation of Abundance Maps in 
Hyperspectral Imaging", in Proceedings of the 4th Workshop on Hyperspectral 
Image and Signal Processing: Evolution in Remote Sensing (WHISPERS 2012), 
Shangai, Chine, 4-7 juin 2012. Best Paper Award.


For the USGS library, please cite:

# R. N. Clark, G. A. Swayze, A. Gallagher, T. V. King, and W. M. Calvin,
"The U.S. geological survey digital spectral library: version 1: 0.2 to 3.0
um," U.S. Geological Survey, Denver, CO, Open File Rep. 93-592, 1993.



---------------------------------------------------------------------------

