How can i convert the edge line of this image from white to black and the background from black to white?

I just completed a code and it ran ok, but i have a slight issue with it. the code is to extract the edge of the image of an object in Fourier domain.the code is written below and the image used in the code is attached.

the problem i have with it is to convert the color of the edge line of the resulting image from white to black and the background from black to white.

kindly help insert the appropriate code in the appropriate line to help do the conversion.

% Read in a standard image
Standardimage = 'AEESS2.jpg';
Originalimage = imread(Standardimage);
% Display the original image
imshow(Originalimage);
%Convert Original image to grayscale and display.
grayImage = rgb2gray(Originalimage);
imshow(grayImage);
% Display the original grayscale image.
subplot(2, 2, 1);
imshow(grayImage, [0 255]);
title('Original Grayscale Image in its Spatial Domain', 'FontSize', 10);
% Enlarge the figure to full screen.
% set(gcf, 'Position', get(0,'Screensize'));
set(gcf, 'units','normalized','outerposition',[0 0 1 1]);
% Compute the FFT.
FFTImage = fft2(grayImage);
% Shift the zero frequency location from (0,0)to the center of the display
% and take log in order to have a clearer display.
centeredFFTImage = log(fftshift(real(FFTImage)));
% Display the FFT image.
subplot(2, 2, 2);
imshow(centeredFFTImage, []);
title('Visually Enhanced Frequency Domain of the Original Grayscale Image', 'FontSize', 9);
% Zero out the corners.
window = 30;
FFTImage(1:window, 1:window) = 0;
FFTImage(end-window:end, 1:window) = 0;
FFTImage(1:window, end-window:end) = 0;
FFTImage(end-window:end, end-window:end) = 0;
% Shift the zero frequency location from (0,0)to the center of the display
% and take log in order to have a clearer display.
centeredFFTImage = log(fftshift(real(FFTImage)));
subplot(2, 2, 3);
imshow(centeredFFTImage, []);
title('Visually Enhanced Frequency Domain of the Filtered image', 'FontSize', 10);
% Taking the Inverse FFT to convert the high pass filtered
%image back to Spatial domain.
output = ifft2(FFTImage);
% Display the output.
subplot(2, 2, 4);
imshow(real(output), [0 255]);
title('High Pass Filtered Image converted back to the Spatial Domain', 'FontSize', 10);

Thanks, Best Regards.

[Image Analyst]

Your image, AEESS2.jpg, is NOT attached. Did you forget to click both the choose file button and the attach file button?

Answer 1

[Image Analyst]

Can't you just invert your image:

output = 255 - real(output);

That will invert black and white.

[Dipps]

<</matlabcentral/answers/uploaded_fi

les/7881/AEESS2.jpg>>

Thanks for your response. I actually clicked the file but there were issues with my internet which caused the pictures not to be attached plus I dint get to know on time.

The line of code inverted the image. I have attached the resulting image but it has lots of ripples around it. I tried it on other images and their result also came out with ripples. Please how and what codes can I use to eliminate the ripples.

Thanks

[Image Analyst]

You seem to be just wanting to get an edge detection image. Why are you doing this in the Fourier Domain? Just use edge() or imgradient() and you most likely won't get ripples.

The reason you get ripples is you're multiplying by a rect() function, which is the same as convolving with a sinc() function in the spatial domain - hence the ripples. You could reduce them by zeroing out with a Gaussian. This would soften the edges and you'd be convolving with a Gaussian in the spatial domain which doesn't have ripples, because Gaussians don't have ripples like sinc functions do.

[Dipps]

Yes I got your point, personally I wouldn't like prolonging issues working in the Fourier domain but I was specifically given the instruction to carry out my edge detection in the Fourier domain propably because someone else had worked on edge detection in the spatial domain and there's no need to repeat what someone has done before.

That why I have to do my edge detection in the Fourier domain and perfect it to make it have a better or similar result with the spatial domain.

I've been working on this FD for a while now and I think am close to completion, its just the elimination of the ripples that remain.

Kindly help suggest the best line of codes to remove the ripples.

Thanks

[Image Analyst]

If you just want the edges, then you can threshold. The ripples will probably be small and below the threshold so you won't see them.

[Dipps]

OK I will try that. Is there a way I can increase the thickness of the edge line? What code or command can I use?

Thanks

[Image Analyst]

Once you've thresholded, you can use imdilate().

[Dipps]

what better codes can I use to threshold please? The one I used (im2bw() ) is not giving a good result. Please help.

Thanks

Regards

[Image Analyst]

Just threshold on your own

binaryImage = grayImage > thresholdValue; % Can use < if you want.

[Dipps]

Good day Sir;

Thanks for your previous assistance, you've really been kind to me, i really appreciate your effort.

Work is still on going on my code, Please i need a matlab code to extract ONLY the edge of this leaf without the ribs inside the leaf.

Will really appreciate it if you can help with the codes.

Secondly, I need the codes to analyze independently each color of the rgb image, instead of mixing all of them constructing a gray image because i feel there are lost of information by converting the image to grayscale before using it in the program.

Kindly help make necessary alteration to the codes below.

Thanks in anticipation of your help.

Best Regards

% Read in a standard image Standardimage = 'leaf3.jpg'; Originalimage = imread(Standardimage); % Display the original image imshow(Originalimage); %Convert Original image to grayscale and display. grayImage = rgb2gray(Originalimage); imshow(grayImage); % Display the original grayscale image. subplot(2, 2, 1); imshow(grayImage, [0 255]); title('Original Grayscale Image in its Spatial Domain', 'FontSize', 10); % Enlarge the figure to full screen. % set(gcf, 'Position', get(0,'Screensize')); set(gcf, 'units','normalized','outerposition',[0 0 1 1]); % Compute the FFT. FFTImage = fft2(grayImage); % Shift the zero frequency location from (0,0)to the center of the display % and take log in order to have a clearer display. centeredFFTImage = log(fftshift(real(FFTImage))); % Display the FFT image. subplot(2, 2, 2); imshow(centeredFFTImage, []); title('Visually Enhanced Frequency Domain of the Original Grayscale Image', 'FontSize', 9); % Zero out the corners. window = 30; FFTImage(1:window, 1:window) = 0; FFTImage(end-window:end, 1:window) = 0; FFTImage(1:window, end-window:end) = 0; FFTImage(end-window:end, end-window:end) = 0; % Shift the zero frequency location from (0,0)to the center of the display % and take log in order to have a clearer display. centeredFFTImage = log(fftshift(real(FFTImage))); subplot(2, 2, 3); imshow(centeredFFTImage, []); title('Visually Enhanced Frequency Domain of the Filtered image', 'FontSize', 10); % Taking the Inverse FFT to convert the high pass filtered %image back to Spatial domain. output = ifft2(FFTImage); output1 = 255 - real(output); % Display the output. subplot(2, 2, 4); imshow(real(output1), [0 255]); title('High Pass Filtered Image converted back to the Spatial Domain', 'FontSize', 10);

[Image Analyst]

No need to do that in the Foureir domain when you can simply do it in the spatial domain with the proper kernel. Attached (below in blue) is the code to find the border and do the spatial filter.

It's hard to see the final image because it's shrunk down and most of the pixels were lost to subsampling.

[Dipps]

Thanks so much sir, i really appreciate your gesture. You've been of great help to me. God bless u. I've been having issues with internet thats why this is coming late.

Am really making good progress in my matlab codes now, much thanks to you. will keep you posted on my results soon.

Thanks

Best Regards