how to calculate entropy of colored image?

33 views (last 30 days)
sweta arya
sweta arya on 29 Dec 2015
Commented: Jordan Rashid on 23 Oct 2018
how to calculate entropy of colored image?

Answers (2)

A. P. B.
A. P. B. on 23 Jun 2017
Edited: A. P. B. on 23 Jun 2017
Assuming input_image is the name of the input. Entropy of each channel can be found using : Entropy_Red_Channel=Entropy(input_image(:,:,1)).
For each channel R,G and B you can calculate them separately. You can calculate entropy for multidimensional image but the function entropy will consider each of them as gray scale not RGB. Finally you can average the per channel entropy.

Jordan Rashid
Jordan Rashid on 6 Sep 2018
Unless you account for the mutual information between channels, the solutions posted here will overestimate the total entropy.
  2 Comments
Francisca Rey
Francisca Rey on 23 Oct 2018
How can you take into consideration the mutual information between channels?
Jordan Rashid
Jordan Rashid on 23 Oct 2018
https://en.wikipedia.org/wiki/Mutual_information#Relation_to_conditional_and_joint_entropy
The calculations include many more terms as you increase the number of channels.

Sign in to comment.

Categories

Find more on Image Processing Toolbox in Help Center and File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!