How do I threshold the image automatically based on its energy content?

Say my threshold is taking in those components that constitute about 75% of energy of image and making the remaining as zero.How do I do that?

Answer 1

[Image Analyst]

D_coder, try this:

clc;    % Clear the command window.
clearvars;
close all;  % Close all figures (except those of imtool.)
workspace;  % Make sure the workspace panel is showing.
format long g;
format compact;
fontSize = 20;

grayImage = imread('cameraman.tif');
subplot(2, 2, 1);
imshow(grayImage);
title('Original Image', 'FontSize', fontSize);
sortedGrayLevels = double(sort(grayImage(:), 'descend'));
% Sum up the energy from most energetic to least energy.
percentage = cumsum(sortedGrayLevels);
percentage = percentage / percentage(end);
subplot(2, 2, 2);
plot(percentage, 'b-', 'LineWidth', 2);
grid on;
title('Cumulative Distribution Function', 'FontSize', fontSize);

% Find the brighter 75%
% Find the gray level where 75 percent is
index75 = find(percentage >= 0.75, 1, 'first')
grayLevel75 = grayImage(index75)

% threshold the most energy 75%
binaryImage = grayImage > grayLevel75;
subplot(2, 2, 3);
imshow(binaryImage);
title('Brighter 75%', 'FontSize', fontSize);

% Find the darker 75%
% Find the gray level where 75 percent is
index75 = find(percentage >= 0.25, 1, 'first')
grayLevel25 = grayImage(index75)

% threshold the most energy 75%
binaryImage25 = grayImage < grayLevel25;
subplot(2, 2, 4);
imshow(binaryImage25);
title('Darker 75%', 'FontSize', fontSize);

Each binary image will contain 75% of the energy. It just depends if you wanted to start with the darker pixels and work brighter, or start with the brightest pixels and work darker.

[Christie John Jacob]

While using this code matlab displayed an error message that there is error in imshow function

' Error using images.internal.imageDisplayValidateParams>validateCData (line 119)

If input is logical (binary), it must be two-dimensional.

Error in images.internal.imageDisplayValidateParams (line 27)

common_args.CData = validateCData(common_args.CData,image_type);

Error in images.internal.imageDisplayParseInputs (line 78)

common_args = images.internal.imageDisplayValidateParams(common_args);

Error in imshow (line 245)

images.internal.imageDisplayParseInputs({'Parent','Border','Reduce'},preparsed_varargin{:});

Error in gray (line 27)

imshow(binaryImage) '

Why is this coming ?

[Image Analyst]

I just copied and ran the code and it ran beautifully. You must have altered it somehow. Maybe you read in a true color RGB image instead of a gray scale image to fix that, put this right after the call to imread():

% Get the dimensions of the image.
% numberOfColorChannels should be = 1 for a gray scale image, and 3 for an RGB color image.
[rows, columns, numberOfColorChannels] = size(grayImage);
if numberOfColorChannels > 1
	% It's not really gray scale like we expected - it's color.
	% Use weighted sum of ALL channels to create a gray scale image.
	grayImage = rgb2gray(grayImage);
	% ALTERNATE METHOD: Convert it to gray scale by taking only the green channel,
	% which in a typical snapshot will be the least noisy channel.
	% grayImage = grayImage(:, :, 2); % Take green channel.
end