How can I get the minimum enclosing circle with OPENCV?

Question

I'm using cv::minEnclosingCircle(...) in order to get the minimum circle that exactly evolves my contour, but I'm getting a circle a little big bigger.

In other words, I'm trying to get something like this:

https://upload.wikimedia.org/wikipedia/commons/thumb/3/35/Simple_concave_polygon_Min_Enclosing_Circle.svg/441px-Simple_concave_polygon_Min_Enclosing_Circle.svg.png

But I'm getting this (the circle):

Note how the circle is a little bigger than the item to enclose.

I need to enclose my object into a circle, not an ellipse.

Thank you in advance.

This is my code:

cv::vector<cv::Point> allPixels;
    int columnas = img.cols, filas = img.rows;
    cv::Point pt;
    for(int col = 0; col < columnas; col++){
        for(int row = 0; row < filas; row++){

            int val = img.at<uchar>(row,col);

            if(val == 255){
                pt.x = col;
                pt.y = row;

                allPixels.push_back(pt);
            }
        }
    }

    cv::Mat dispImage = img.clone();
    cv::Point2f center;
    float radius;

    cv::minEnclosingCircle(allPixels,center,radius);

    cv::circle(dispImage,center,radius,cv::Scalar(128),1);
    cv::circle(dispImage,center,1,cv::Scalar(128),1);

    cv::imwrite("Enclosing_Result.png",dispImage);

With 'img' a cv::Mat with size (760,760) and format CV_8UC1. The final result ("Enclosing_Result.png") is next:

And my target is which follows (drawn):

you should show your code. – apple apple Nov 23 '17 at 14:42 — apple apple, Nov 23 '17 at 14:42

Kinght 金 · Answer 1 · 2018-12-07T03:05:41.603

1

My result is OK.

1. for only one region

## only one region
cnts = cv2.findContours(threshed, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[-2]

(x,y), r = cv2.minEnclosingCircle(cnts[0])

2. for more than one region

## more than one region
mask = threshed.copy()

## find centers 
for cnt in cnts:
    (x,y), r = cv2.minEnclosingCircle(cnt)
    pt = (int(x), int(y))
    centers.append(pt)

## connect the `centers`
for i in range(1, len(centers)):
    cv2.line(mask, centers[i-1], centers[i], 255, 2)

## find the center 
cnts = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[-2]
(x,y), r = cv2.minEnclosingCircle(cnts[0])

edited Dec 07 '18 at 03:05

answered Nov 24 '17 at 05:52

Kinght 金

17,681
4
60
74

That's Python, isn't it? – areify Nov 24 '17 at 07:52
Yeah, I just have a test, it's ok. – Kinght 金 Nov 24 '17 at 07:53
OK but what about an image with different contours? I want to get something like this: http://oi67.tinypic.com/296cghe.jpg – areify Nov 24 '17 at 08:32
You need more steps for this image: Connect the "centers", then do `minEnclosingCircle` again. – Kinght 金 Nov 24 '17 at 09:21
Thanks for editing. I've done similar steps. Instead of using lines I've used the minimimum enclosing circle of each contour, and then the minimum of all of them. But I'm still having the same problem: the circle is always a little bit bigger than the contour (I'm using C++-CLI). Maybe I'm using wrong parameters? Thank you. – areify Nov 24 '17 at 09:45
Whatever, my result is OK. – Kinght 金 Nov 24 '17 at 11:12
Why the difference between C++ and Python? – areify Nov 24 '17 at 11:35
Because my method is different from yours, not the language. – Kinght 金 Nov 24 '17 at 12:05
The method for connecting separated regions is wrong, this result is a lucky guess. It will not work in a case [like this](https://i.imgur.com/V3HCFSZ.png) – The Data Scientician Jun 27 '18 at 09:29

How can I get the minimum enclosing circle with OPENCV?

1 Answers1

1. for only one region

2. for more than one region

Linked