cv. Houghcircles: Circular Hough transform opencv

  The basic principle ：

For every point on the circumference , Find its gradient , According to the gradient, the tangent line about this point can be made , The direction perpendicular to the tangent is the gradient like direction , The intersection of the gradient direction of each point is the center of the circle , Then the radius can be determined according to the position of the center of the circle .

Straight line Hough change ：

Images Hough Transformation _ A lonely blog -CSDN Blog

function ：

circles=cv.HoughCircles(image, method, dp, minDist[, param1[, param2[, minRadius[, maxRadius]]]]])

image： Grayscale image 
method： It's usually cv.HOUGH_GRADIENT
dp: Inverse ratio between accumulator resolution and image resolution , It's usually 1
minDist： The minimum distance between different center points , Too often some circles are omitted , Too small will produce many unrelated circles 
param1： Pass to  canny  High threshold of edge detection operator , The low threshold is half of the high threshold 
param2： It is the cumulative threshold of the circle center in the detection stage . The smaller the size, the more false circles can be detected . The larger the circle that can pass the test, the closer it is to the perfect circle .
minRadius： Minimum radius 
maxRadius： Maximum radius 

  example ：

import cv2.cv2
import numpy as np
import cv2 as cv
from matplotlib import pyplot as plt

img1 = cv.imread(r'XXXXX.jpg')
img=img1.copy()
img = cv.cvtColor(img, cv.COLOR_BGR2GRAY)

img = cv.medianBlur(img,5)
cimg = cv.cvtColor(img,cv.COLOR_GRAY2BGR)
circles = cv.HoughCircles(img,cv.HOUGH_GRADIENT,1,300,
                            param1=50,param2=30,minRadius=50,maxRadius=200)
circles = np.uint16(np.around(circles))
for i in circles[0,:]:
    #  A circle ：
    cv.circle(img1,(i[0],i[1]),i[2],(0,255,0),5)
    #  center of a circle ：
    cv.circle(img1,(i[0],i[1]),2,(0,0,255),5)
cv.imshow('detected circles',img1)
cv.waitKey(0)
cv.destroyAllWindows()