NORMALIZED CROSS CORRELATION AS A SIMILARITY MEASURE TO FIND SCORE MATRIX

Hello everyone. I've 2 face images (2 probes) and 100 templates (face images or gallery). I want to compare each probe with all the 100 galleries. For eg, Probe 1 will be compared with 100 galleries, then probe2 will be compared to 100 galleries. I'm using normalized cross correlation for this purpose. The size of each image is 50*50. Although, I'm not sure about the further steps (What to be done after getting correlation matrix). I found the maximum number in the corrleation matrix, but I dont know how to get the score matrix for calculating genuine and impostor scores. I wrote this code, although I don't think this is right. Please can someone explain this?

%Storing the first two probe images

a1=imread('C:\Users\ritvikpalvankar7\Desktop\Fundamentals of Biometric identification\HW3\probeset\subject1_img2.pgm');

a2=imread('C:\Users\ritvikpalvankar7\Desktop\Fundamentals of Biometric identification\HW3\probeset\subject1_img3.pgm');

%Storing the gallery image one by one

genuine_score = [];

imposter_score = [];

Score1 = zeros(100,100);

Score2 = zeros(100,100);

for i=1:100

a3=imread("C:\Users\ritvikpalvankar7\Desktop\Fundamentals of Biometric identification\HW3\galleryset\subject"+i+"_img1.pgm");

col=1;

c1 = normxcorr2(a3,a1);

c2 = normxcorr2(a3,a2);

v1 = max(max(c1));

v2 = max(max(c2));

Score1(i,col) = v1;

col=col+1;

Score1(i,col) = v2;

col=col+1;

if i==j

genuine_score = [genuine_score v1];

genuine_score = [genuine_score v2];

else

imposter_score = [imposter_score v1];

imposter_score = [imposter_score v2];

end

if v1 > v2

Score2(i,col-2) = v1;

else

Score2(i,col-2) = v2;

end

Score2 = Score2(:,any(Score2));

end