How would I extract the circular area of a binary image which looks like:

enter image description here

The two rods emerging from the side of the circle are noise.

I know of the hough transform in Matlab. However, I am using R and can't seem to find anything similar.

Ideas anyone?

  • $\begingroup$ This is an R specific question, and I think you're going to get a better response on Stack Overflow. Should I migrate it? $\endgroup$ – Phonon Mar 12 '13 at 23:54
  • $\begingroup$ I guess it has a bit of both. Sure though $\endgroup$ – by0 Mar 13 '13 at 18:20

On page 4 of this document describing the R PET package, there's documentation of the Hough transformation. That's probably what you want.

  • 1
    $\begingroup$ I'm a little confused on how to use this for detection of circles $\endgroup$ – by0 Mar 13 '13 at 18:32
  • $\begingroup$ How to call the function or how to install it? $\endgroup$ – Scott Mar 13 '13 at 19:22
  • $\begingroup$ I understand how to do both. The returned data is a matrix of parameters of the the original matrix. Am I correct? How do I use that to approximate circles in the image $\endgroup$ – by0 Mar 13 '13 at 19:51

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.