0

I just want to know what will the difference be if instead of using hough circle to detect a circle, I find a contour and using minEnclosed circle find the circle? Which one will be more accurate? As far as I can understand both of them should give me the same thing. Can anyone help clarify

Kshitij Patil
  • 91
  • 8

1 Answers1

3

minEnclosed circle will enclose all outlier points in your connected component (blob or edge) while Hough circle searches for the best fit using voting algorithm.

So for searching circles; Hough circle is more accurate.

Edit :

enter image description here

Ziri
  • 718
  • 7
  • 16
  • what abt when I know I have a circle and just need its dimensions can I use the method mentioned above where I take a counotur and use it to find the centre and radius – Kshitij Patil Dec 03 '19 at 06:45
  • If you already sure it's circle just use cv::minEnclosingCircle(...) it will return center and radius – Ziri Dec 03 '19 at 06:49
  • 1
    if you know which pixel belong to your circle (e.g. a contour without outliers), minEnclosingCircle is very nice. If you know the number of circles in your and and which pixels might belong to the border/edges of your circle, but you have outliers, RANSAC is very nice (and often quite accurate). If you know basically nothing and want to find out, whether there are any circles in your image, houghCircle is very nice. For RANSAC, see my answers here: https://stackoverflow.com/a/20734263/2393191 and https://stackoverflow.com/a/26234137/2393191 and https://stackoverflow.com/q/34650697/2393191 – Micka Dec 03 '19 at 10:43