MATLAB: Can anyone explain the following code

repmat

for i = 1:K
idx = find(DAL(:,K+1) == i);
X(idx,:) = repmat(CENTS(i,:),size(idx,1),1); 
end
full code is given below:
clc
clear all
close all
%%Load Image
[filename,pathname]=uigetfile({'*.*';'*.bmp';'*.tif';'*.gif';'*.png'},'Pick an Image File');
I= im2double(imread([pathname,filename]));
size(I)
[nrows,ncols,colorchannels]=size(I);
F = reshape(I,nrows*ncols,colorchannels);         
size(F)
K     = 8;                                            % Cluster Numbers
CENTS = F( ceil(rand(K,1)*size(F,1)) ,:);             % Cluster Centers
DAL   = zeros(size(F,1),K+2);                         % Distances and Labels
KMI   = 10;                                           % K-means Iteration
for n = 1:KMI
   %first step is to find nearby cluster for each pixel
    for i = 1:size(F,1)        
      for j = 1:K  
        DAL(i,j) = norm(F(i,:) - CENTS(j,:));    %compare the distance between every pixel value with cluster centre.   
      end
        [Distance, CN] = min(DAL(i,1:K));               % 1:K are Distance from Cluster Centers 1:K 
        DAL(i,K+1) = CN;                                % K+1 is Cluster Label
        DAL(i,K+2) = Distance;                          % K+2 is Minimum Distance
      end
     for i = 1:K
        A = (DAL(:,K+1) == i);                          % Cluster K Points
        CENTS(i,:) = mean(F(A,:));   % New Cluster Centers
        if sum(isnan(CENTS(:))) ~= 0                    % If CENTS(i,:) Is Nan Then Replace It With Random Point
           NC = find(isnan(CENTS(:,1)) == 1);           % Find Nan Centers in first column of cents
           for Ind = 1:size(NC,1)
           CENTS(NC(Ind),:) = F(randi(size(F,1)),:);
           end
        end
     end
  end
X = zeros(size(F));
for i = 1:K
idx = find(DAL(:,K+1) == i);
X(idx,:) = repmat(CENTS(i,:),size(idx,1),1); 
end
T = reshape(X,nrows,ncols,colorchannels);
%%Show
figure()
subplot(121); imshow(I); title('original')
subplot(122); imshow(T); title('segmented')
disp('number of segments ='); disp(K)

Best Answer

With ‘K’ defined as 8, this segment:
for i = 1:K
    idx = find(DAL(:,K+1) == i);
    X(idx,:) = repmat(CENTS(i,:),size(idx,1),1); 
end
searches all rows of the ‘K+1’ column of ‘DAL’ for a value that equals the index ‘i’. (The comparison will only match integer values.) It then creates matrix ‘X’ length ‘idx’ rows at a time, using the value ‘idx’ (that is apparently a column vector) returned from the find call to define the rows. It then uses the repmat (essentially ‘replicate matrix’) function to create duplicates of the row vector ‘CENTS(i,:)’ to the row size of the ‘idx’ vector. The 1 as the last argument means that the function creates a vertical (row) replication only, not row-and-column replication.
I added the indentation to make the code easier to read.
Related Question