how do I select only the segmented region from a original image in MATLAB

3 vues (au cours des 30 derniers jours)
I need a little help.
I have a MATLAB code in which I've segment out an original image into multiple segments. Now I want to select only a specific segmented area and give it as an input to my function. I have attached my segmented image in which desired part is shown along with the black pixels. How do I select only the desired region, I don't want black pixels region.
Thanks,
for k = 1:max(max(l))
color = img;
color(rgb_label ~= k) = 0;
segmented_images{k} = color;
image = double(segmented_images{k})/255.0;
end

Réponse acceptée

Matt J
Matt J le 20 Juin 2021
You could do,
S=regionprops(rgb_label,img,'Image')
  4 commentaires
kashif Mobeen
kashif Mobeen le 20 Juin 2021
How can I display every region?
imshow(S(1))??
imshow(S(2))??
......
Matt J
Matt J le 20 Juin 2021
Modifié(e) : Matt J le 20 Juin 2021
For example,
for k=1:numel(S)
figure(i); imshow(S(k).Image)
end

Connectez-vous pour commenter.

Plus de réponses (1)

Image Analyst
Image Analyst le 20 Juin 2021
You could do
mask = max(rgbImage, [], 3) > 0;
[r, c] = find(mask); % Find rows and columns of non-zero pixels
row1 = min(r);
row2 = max(r);
col1 = min(c);
col2 = max(c);
croppedImage = rgbImage(row1:row2, col1:col2, :);
  5 commentaires
Matt J
Matt J le 20 Juin 2021
No, there is no such thing as a non-rectangular image.
Image Analyst
Image Analyst le 20 Juin 2021
Matt's right. Why do you want that anyway? Do you want transparent pixels, like I think PNG images can have so that you can see the background. I never do that since it has no real use in image analysis. If you think you need transparent pixels, explain why? Because I would counter that you don't, even though you think you might. It's not necessary to do any kind of image analysis on the image.

Connectez-vous pour commenter.

Catégories

En savoir plus sur Image Processing Toolbox dans Help Center et File Exchange

Community Treasure Hunt

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

Start Hunting!

Translated by