Enhance the image with non-linear function

Hello everyone, I'm a beginner in using Matlab and I want to know if what I did in solving this question right or wrong:

the question says:

Implement and test a method with the following specification. Input: A gray scale image Processing: Enhance the image with non-linear function Output: Enhanced image In the implementation follow the steps given below:

• Read the image Im
• The image will be in uint8 format. Convert it into double and transform the range of gray scale into [-1 1]. Call it TIm
• Compute the max of the absolute values of the transformed image Tim i.e. max{|Tim|}.
• Define a threshold as T = t x mean{|Tim|}, where t is user-defined and must be in the range (0,1). Try different values of t.

*Enhance the image using the following function:

where k > 1 is also user-defined. Try different values of k. Test different values of t and k to find the values which give the best enhancement results. Preparer a report showing the results with different values of t and k, and also write the comments on the behavior of these parameters for enhancement. __________

I solved the first four points as follows:

% Close images and clear the workspace, if there are any active contents
clc; clear all; close all;

% Read the image Im
Im = imread('noise_field.jpg');

%Convert it into double and transform the range of gray scale into [-1 1]
Imt = double(Im);
Tim = mat2gray(Imt, [-1, 1]);

%Compute the max of the absolute values of the transformed image Tim
MaxTim = max(abs(Tim));

%Define a threshold as T = t x mean{|Tim|}
t=double(0.1);
T= t*mean(Tim);

The last point I really have no idea about how to do it:(

Is my code correct?! I appreciate your help

[Rena Berman]

(Answers dev) Restored question.

Answer 1

[Image Analyst]

No. max() gives the max column-by-column so you need to transform it into a column vector:

% Compute the max of the absolute values of the transformed image Tim
MaxTim = max(abs(Tim(:)));

%Define a threshold as T = t x mean{|Tim|}
t = 0.1;
T = t*mean(Tim(:));

% Compute binary map of different intensity ranges
darkPixels = Tim < -T;
mediumPixels = abs(Tim) < T;
brightPixels = Tim > T;

% Now create a new image
enhancedTim = zeros(size(Tim));
% Assign dark pixels
enhancedTim(darkPixels) = Tim + (k-1)*T;
% Do the same for medium and bright pixels with their formulas.

To get t and k, adapt this:

% Ask user for two floating point numbers.
defaultValue = {'45.67', '78.91'};
titleBar = 'Enter a value';
userPrompt = {'Enter floating point number 1 : ', 'Enter floating point number 2: '};
caUserInput = inputdlg(userPrompt, titleBar, 1, defaultValue);
if isempty(caUserInput),return,end; % Bail out if they clicked Cancel.
% Convert to floating point from string.
usersValue1 = str2double(caUserInput{1})
usersValue2 = str2double(caUserInput{2})
% Check for a valid number.
if isnan(usersValue1)
    % They didn't enter a number.  
    % They clicked Cancel, or entered a character, symbols, or something else not allowed.
  % Convert the default from a string and stick that into usersValue1.
    usersValue1 = str2double(defaultValue{1});
    message = sprintf('I said it had to be a number.\nI will use %.2f and continue.', usersValue1);
    uiwait(warndlg(message));
end
% Do the same for usersValue2

If you're still stumped, let me know.

[Lara Adms]

Thank you very much. I don't know how can I thank you,that was very helpful and I learned a lot from you <3

[Lara Adms]

Please sir can you till me how can I delete my question and if that is Ok with you

[Walter Roberson]

No, questions will not be deleted once posted, not unless they violate the terms of the site. If you wanted private consultation you should have paid a private consultant.