how to find entropy of X.

how i implement this entropy formula(PNG file atached) in matlab code

my X is Column c in xlsx file(attached) i want to find for 1000 value

[John D'Errico]

Why not just download the yalmip toolbox, which has entropy already implemented? Is here for download:

https://yalmip.github.io

[john karli]

i did't find

[Walter Roberson]

See the comments of

https://www.mathworks.com/matlabcentral/fileexchange/28692-entropy

there is an implementation in the comments .

There is a function in the image processing toolbox for the greyscale image case.

[john karli]

Thankx alot its work for me y = [1 -6011 -3000 2592]):

this code find the entropy

function [ent] = EntropyInt(y) 
% Calculate the entropy for an integer value of y 

% First verify that y is truely integer-valued 
Sum = sum(y); 
if( Sum ~= round(Sum) ) 
error('INTEGER_ENTROPY:InvalidInput', 'Input arguments must be of integer value.') 
end
% Generate the histogram 
[n x] = hist(y, double(min(y):max(y))); 

% Normalize the area of the histogram to make it a pdf 
n = n / sum(n); 

% Calculate the entropy 
indices = n ~= 0; 
ent = -sum(n(indices).*log2(n(indices))); 
end

[john karli]

indices = n ~= 0; i did't understand this line what does it mean

[Image Analyst]

log(0) is minus infinity, so n~= zero finds those bins where the value (number of counts in the histogram bin) is non-zero. So only those are passed into log2(), thus preventing a "-inf" result.

[Walter Roberson]

https://www.mathworks.com/help/matlab/math/array-indexing.html#d120e1410

[john karli]

thanks for your answer.. how can i find the join entropy ?

[Image Analyst]

What is that? Do you have a formula?

[john karli]

yes snap shot is attached kindly see

[john karli]

u got it??

Answer 1

[Image Analyst]

You can try entropy() or entropyfilt() in the Image Processing Toolbox, if you have it. entropyfilt() does a sliding window computation of entropy whereas entropy does it for the whole array.

[john karli]

thanks for your ans its related to probability

[Image Analyst]

We know that.