How to crop the coin circular and neglect the rest area?

2 views (last 30 days)
I have a coin image and I want to crop the circular section of the coin, I tried below code but this doesn't worked well.
I want to crop out the coin with the outer boundary with a perfect circle. Any help would be appreciated. Thank you
Code which I tried:
%B1 is in coin.mat coin image
B2 = B1/max(B1(:));
k=B1*200;
k(k>-6000) = 1;
k(k<-6000) = 0;
bw2 = imfill(k,'holes');
figure,imshow(bw2)
bw3 = imopen(bw2, ones(3,3));
figure,imshow(bw3)
bw3 = imopen(bw2, ones(5,5));

Accepted Answer

Image Analyst
Image Analyst on 5 Apr 2023
That's what I do in my popular tutorial.
It's a generic, general purpose demo of how to threshold an image to find blobs (coins), and then measure things about the blobs, and extract certain blobs based on their areas or diameters.

More Answers (1)

Cris LaPierre
Cris LaPierre on 4 Apr 2023
I would use the Image Segmenter app. After loading the image, you can define a circuilar ROI, apply a mask, and export the result back to MATLAB.
Just be aware that the result is always going to be a square, as the image is stored in a matrix. There is no circle version of it. You can use the mask to adjust the background color if you want.
You can learn more in the Using the Image Segmenter App video, which is part of the Image Processing for Engineering and Science Specialization on Coursera. It is a self paced course created by MathWorks, and you can enroll for free.
  3 Comments
shubham kumar gupta
shubham kumar gupta on 5 Apr 2023
Edited: shubham kumar gupta on 5 Apr 2023
I appreaciate the efforts!
This really helped me, but still this poses human error.
Thank you
Image Analyst
Image Analyst on 5 Apr 2023
If extremely high precision is really a requirement then you'd do things to enable that. This includes
  1. Using as high a resolution camera as you can.
  2. Using a telecentric lens (instead of a regular lens).
  3. Using a uniform background of contrasting color (like black velvet).
  4. Using proper lighting.
Alternatively you can use a caliper micrometer.

Sign in to comment.

Categories

Find more on Image Processing and Computer Vision in Help Center and File Exchange

Products


Release

R2023a

Community Treasure Hunt

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

Start Hunting!