Continuing to investigate template matching for the Chiromancer and feel some hope as the last couple of algorithms I've written are pretty good at finding significant features on the palm images, now I'm looking at establishing a significant difference between images, and this looks pretty useful, infact what I am going to use it in the next iteration:

minSAD = VALUE_MAX;



// loop through the search image

for ( int x = 0; x <= S_rows - T_rows; x++ ) {

for ( int y = 0; y <= S_cols - T_cols; y++ ) {

SAD = 0.0;



	// loop through the template image

	for ( int i = 0; i < T_rows; i++ )

	    for ( int j = 0; j < T_cols; j++ ) {



        pixel p_SearchIMG = S[x+i][y+j];



        pixel p_TemplateIMG = T[i][j];



        SAD += abs( p_SearchIMG.Grey - p_TemplateIMG.Grey );

    }

	}



// save the best found position 

	if ( minSAD > SAD ) {

	    minSAD = SAD;

    // give me VALUE_MAX

	    position.bestRow = x;

	    position.bestCol = y;

	    position.bestSAD = SAD;

}

}

The last bit enables a rectangle to be drawn around the best matched region.