2
$\begingroup$

I'm trying to get the internal geometry of cheese from images of its microstructure:

enter image description here

I tried the canny edge detector and otsu thresholding but neither of these worked very well. I'm guessing that I might need something more powerful but I'm not sure what as I'm new to the field of image processing.

In particular, I'd like to get the distribution of the distances between the pores and the spatial distribution of pore size from the image. Those are the two things I'm most interested in obtaining from the picture.

$\endgroup$
  • 2
    $\begingroup$ hm.... these pores do loop like little black circles, don't they? that would be my internet research keyword, "detect circles in image". $\endgroup$ – Marcus Müller Jul 23 '16 at 8:01
  • $\begingroup$ or blob detection in skimage scikit-image.org/docs/dev/auto_examples/plot_blob.html or in openCV learnopencv.com/blob-detection-using-opencv-python-c , 30 seconds in google. $\endgroup$ – Darleison Rodrigues Jul 23 '16 at 21:40
  • $\begingroup$ In my youth, I read about some pattern recognition hardware using holograms and such. Perhaps that work could be refitted the digital realm; which I presume you are in? I sort of guess you would be looking for various sized circles? $\endgroup$ – rrogers Jul 27 '16 at 0:59

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.