改善python opencv中特定颜色的圆圈检测

Question

我想使用霍夫变换来检测该图像中的紫色圆圈（紫色花粉）。

但是结果表明，它也检测出其他因素。

我该怎么做才能改善此圈子检测？

这是我的代码：

import os, sys
import numpy as np
import cv2
from PIL import Image

def circle_detect(path, filename):

    iml = cv2.imread(path,cv2.IMREAD_COLOR)


    img = image_resize(iml,height=960)
    img_array = np.array(img)

    cimg = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
    cimg = cv2.medianBlur(cimg,5)

    #Circle detection to detect pollen in big images, return the center's coordinates and radius of circles in array
    circles = cv2.HoughCircles(cimg,cv2.HOUGH_GRADIENT,1,10,param1=15,param2=20,minRadius=10,maxRadius=25)
    circles = np.uint16(np.around(circles))[0,:]
    for j in range(len(circles)):
        cv2.circle(img,(circles[i][0],circles[i][1]),circles[i][2],(0,255,0),2)

    cv2.imwrite("export_circle/"+"output"+filename,img)

Answer 1

每当您播放彩色图像时，最好选择HSV色彩空间。对于提供的图像，我将图像转换为HSV并获得了色相通道。在此色调频道上查找圈子。

代码：

import cv2

im1 = cv2.imread(r'C:\Users\Jackson\Desktop\pollen.jpg')
#--- convert to hsv color space ---
hsv = cv2.cvtColor(im1, cv2.COLOR_BGR2HSV)

im2 = im1.copy()

#--- find circles in the hue channel ---
circles = cv2.HoughCircles(hsv[:,:,0],cv2.HOUGH_GRADIENT, 1, 75, param1=15, param2=30, minRadius=0,maxRadius=400)
circles = np.uint16(np.around(circles))

for i in circles[0,:]:
        # draw the outer circle
        cv2.circle(im2,(i[0],i[1]),i[2],(0,255,0),2)

        # draw the center of the circle
        cv2.circle(im2,(i[0],i[1]),2,(0,0,255),3)

cv2.imshow("im2", im2)

结果：

您必须调整参数才能正确找到圆