function [eigvector, eigvalue, Y] = LDA(X,gnd)
% LDA: Linear discriminant analysis (Fisherfaces approach PCA+LDA)
%
%       [eigvector, eigvalue] = LDA(X, gnd)
%
%             Input:
%               X     - Data matrix. Each row vector of fea is a data point.
%               gnd   - Colunm vector of the label information for each
%                       data point. 
%
%             Output:
%               eigvector - Each column is an embedding function, for a new
%                           data point (row vector) x,  y = x*eigvector
%                           will be the embedding result of x.
%               eigvalue  - The eigvalue of LDA eigen-problem. 
% 
% 
%       [eigvector, eigvalue, Y] = LDA(X, gnd) 		
%               
%               Y:  The embedding results, Each row vector is a data point.
%                   Y = X*eigvector
%

%	Reference:
%   
%         P. N. Belhumeur, J. P. Hespanha, and D. J. Kriegman, 揈igenfaces
%         vs. fisherfaces: recognition using class specific linear
%         projection,