vca.m

Vector Component Analysis

function [Ae, indice, Rp] = vca(R,varargin)

% Vertex Component Analysis
%
% [Ae, indice, Rp ]= vca(R,'Endmembers',p,'SNR',r,'verbose',v)
%
% ------- Input variables -------------
%  R - matrix with dimensions L(channels) x N(pixels)
%      each pixel is a linear mixture of p endmembers
%      signatures R = M x s, where s = gamma x alfa
%      gamma is a illumination perturbation factor and
%      alfa are the abundance fractions of each endmember.
% 'Endmembers'
%          p - positive integer number of endmembers in the scene
%
% ------- Output variables -----------
% A - estimated mixing matrix (endmembers signatures)
% indice - pixels that were chosen to be the most pure
% Rp - Data matrix R projected.   
%
% ------- Optional parameters---------
% 'SNR'
%          r - (double) signal to noise ratio (dB)
% 'verbose'
%          v - [{'on'} | 'off']
% ------------------------------------
%
% Authors: Jos