Is there other methods to detect circle apart of houghcircles

asked 2015-04-19 10:48:43 -0600

Kailegh gravatar image

updated 2015-04-20 04:59:09 -0600

I am trying to detect circles road signs and I have some issues.

1.- The HoughCircles function detect circles in a gray image, however with the same parameters but the image binarized(the circle is still perfectly visible) it does not detect any circle, i do not why but with a binarized image it fails a lot, any idea why this issues with binary images?

2- to try to correct that i put the dp parameter in 2, and changed the threshold, in the binary image now i detect circles, but it also gives me a lot of false positives, i do not understand what it is the dp parameter or how to use it

3.- If you tell me that there is no way to make it work, i would like to know if there is any other way of detecting circles in an image.

crosspost on stackoverflow

thanks a lot for your help

edit retag flag offensive close merge delete


Could you post an example image and minimal program with your parameters

FooBar gravatar imageFooBar ( 2015-04-19 11:12:56 -0600 )edit

A quick reply

  1. Sorry but that is not correct, the HoughCircles transforms your image to binary image before applying the hough transform to look for possible circles. If not than your hough space would be filled with circle candidates. I think you must be doing something else wrong here.
  2. To get more info on the dp parameter, which influences the accumulator matrix, check this post on wikipedia.
  3. Best thing is to use hough circles, unless you application allows blob based segmentation. Give us some input images please.
StevenPuttemans gravatar imageStevenPuttemans ( 2015-04-20 04:58:50 -0600 )edit