I know how to calculate the entropy of a single image channel. But I want to calculate entropy for each image from a dataset (almost 800), so that the output shows "what percent of images" are in some specific entropy range.
my entropy code: (I'm using MATLAB 2015b)
I= im;
Red = I(:,:,1);
Green = I(:,:,2);
Blue = I(:,:,3);
%I = I(:); % Vectorization of RGB values
p = imhist(Red); % Histogram
p(p == 0) = [ ];% remove zero entries in p
p = p ./ numel(I); % normalize p so that sum(p) is one.
Er = round(-sum(p.*log2(p)),3);
p = imhist(Blue); % Histogram
p(p == 0) = [ ];% remove zero entries in p
p = p ./ numel(I); % normalize p so that sum(p) is one.
Eb = round(-sum(p.*log2(p)),3);
figure(1),imshow(im),title(['Entropy for R channel = ', num2str(Er),', Entropy for B channel = ', num2str(Eb)]);
You can put your code in a for loop:
files = dir('c:\data\*.jpg'); % Or whatever filter will pick your images
for k = 1 : length(files)
im = fullfile(files(k).folder, files(k).name)
im = imread(im);
% Your code %
% but change Er = ... in Er(k) = ... and Eb(k) = ...
% so you can store the results
end
percentage = sum(Er > Eb) / numel(Er) * 100; % Percentage of images with red entropy higher than blue entropy
disp(['Percentage of images with red entropy higher than blue entropy: ' num2str(percentage)])
Be careful because if you post your code as it is, it will try to open 800 figures!!