// This function returns the value of a Mahalanobis Distance minimum
// distance classifier at x, given the mean vectors and covariance
// matrices of the two populations.
 
function [r]= md_disc (x, U1, U2, C1, C2)

   I1 = inv (C1);
   I2 = inv (C2);
   g1 = sqrt ((x-U1)' * I1 * (x-U1));
   g2 = sqrt ((x-U2)' * I2 * (x-U2));
 
   r = g1 - g2;