Trying to detect all the circles with HoughCircles in openCV (python)

user_13923824 0
Viewed 925

I am following this tutorial: https://www.pyimagesearch.com/2014/07/21/detecting-circles-images-using-opencv-hough-circles/

I was playing around with the parameters ( even those you don't see in the code ex: param2) of HoughCircles and it seems very innacurate, in my project, the disks you see on the picture will be placed on random spots and i need to be able to detect them and their color.

Currently i am only able to detect few circles, and sometimes some random circles are drawn where there is no circles so i am a bit confused.

Is this the best way to do circle detection with openCV or is there a more accurate way of doing it ? Also why is my code not detecting every circles ?

Initial board : https://imgur.com/BrPB5Ox

Circle drawn : https://imgur.com/dT7k29E

My code :

import cv2
import numpy as np


img = cv2.imread('Photos/board.jpg')
output = img.copy()

gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# detect circles in the image
circles = cv2.HoughCircles(gray, cv2.HOUGH_GRADIENT, 1.2, 100)
# ensure at least some circles were found
if circles is not None:
    # convert the (x, y) coordinates and radius of the circles to integers
    circles = np.round(circles[0, :]).astype("int")
    # loop over the (x, y) coordinates and radius of the circles
    for (x, y, r) in circles:
        # draw the circle in the output image, then draw a rectangle
        # corresponding to the center of the circle
        cv2.circle(output, (x, y), r, (0, 255, 0), 4)
        cv2.rectangle(output, (x - 5, y - 5), (x + 5, y + 5), (0, 128, 255), -1)
    # show the output image
    cv2.imshow("output", np.hstack([img, output]))
    cv2.waitKey(0)

Thanks a lot.

computer-vision detection opencv python
2 Answers

First of all you can not expect HoughCircles to detect all circles in different type of situations. It is not an AI. It has different parameters according to get desired results. You can check here to learn more about those parameters.

HoughCircles is a contour based function so you should be sure the contours are being detected properly. In your example I am sure bad contour results will come up because of the lighting problem. Metal materials cause light explosion in image processing and this affects finding contours badly.

What you should do:

  • Solve the lighting problem
  • Be sure about the HoughCircle parameters to get desired output
  • Instead of using HoughCircle you can detect each contour and their mass center ( moments help you to find their mass center). Then you can measure each length of contour points to that mass center if all equal then its a circle.
user_110488870

Hough transform works best on monochromatic/binary image, so you may want to preprocess it with some sort of threshold function. Parameter values for the function are very important for proper recognition.

Is this the best way to do circle detection with openCV or is there a more accurate way of doing it ? Also why is my code not detecting every circles ?

there's also findContours function https://docs.opencv.org/master/d3/dc0/group__imgproc__shape.html#gadf1ad6a0b82947fa1fe3c3d497f260e0 which, to my liking, is more robust and general; you may want to give it a try

user_150733910
Related