function [ OUT ] = quantize( T )
%QUANTIZE Summary of this function goes here
% 
% T is NVx192 matrix encoding NV 8x8 blocks
% each row vector correspondes to a 8x8 block in RGB - i.e. 8x8x3=192
% columns 1:64 are red, columns 65:128 are blue, columns 129:192 blue
% the 8x8 block is scanned by row
%
% OUT has the same structure of T and returns the NV 8x8 blocks
% encoded in screen 2 of a TMS9918

% RGB palette of the TMS9918
pal = [ 0, 0, 0
        0, 0, 0
        0, 241, 20
        68, 249, 86
        85, 79, 255
        128, 111, 255
        250, 80, 51
        12, 255, 255
        255, 81, 52
        255, 115, 86
        226, 210, 4
        242, 217, 71
        4, 212, 19
        231, 80, 229
        208, 208, 208
        255, 255, 255 ];



% number of blocks to be converted
NV = size(T,1);

C = uint8(zeros(size(T)));

R = T(:,1:64);
G = T(:,65:128);
B = T(:,129:192);

% encode each block individually
for j=1:NV
    r = uint8(zeros(1,64));
    g = uint8(zeros(1,64));
    b = uint8(zeros(1,64));
   
    % encode each block line by line
    for n=0:7
        t = [(n*8):(n*8+7)] + 1;
       
        p = [ R(j,t)' G(j,t)' B(j,t)']; % this is 8x3 matrix representing a line
       
        % scan all possible couples of colors for each line
        % the couples of backgound-foreground colors are numbere
        % avoiding duplications  - there are 105 possibilities
        dold=1e41;
        for c1=2:16;
            for c2=(c1+1):16;
                c = [pal(c1,:) ; pal(c2,:)]; % this is 2x3 matrix with the 2 tentative colors
                [x,i]=min(distfun(p,c)');     % associate the 8 points to the closest of the 2 colors
                d=sum(x);
                if d<dold
                    cold=c;
                    dold=d;
                    iold=i;
                end
            end
        end
        r(t) = uint8(cold(iold,1));
        g(t) = uint8(cold(iold,2));
        b(t) = uint8(cold(iold,3));       
    end
    C(j,:) = [r g b];
end
OUT=C;


%%%%%%%%%%%%

function D = distfun(X, C)
%DISTFUN Calculate point to cluster centroid distances.

[n,p] = size(X);
D = zeros(n,size(C,1));
clusts = 1:size(C,1);

for i = clusts
    D(:,i) = sum((double(X) - double(C(repmat(i,n,1),:))).^2, 2);
end