使用OpenCV Python裁剪图像中的圆形

Question

我希望在以下图片中裁剪圆形：

我的代码可以检测出圆形，但无法将其裁剪：

import cv2
#import cv2.cv as cv
img1 = cv2.imread('amol.jpg')
img = cv2.imread('amol.jpg',0)
gray = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(gray, 50, 255, cv2.THRESH_BINARY)

edges = cv2.Canny(thresh, 100, 200)
#cv2.imshow('detected ',gray)
cimg=cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
circles = cv2.HoughCircles(edges, cv2.HOUGH_GRADIENT, 1, 10000, param1 = 50, param2 = 30, minRadius = 0, maxRadius = 0)
for i in circles[0,:]:
    i[2]=i[2]+4
    cv2.circle(img1,(i[0],i[1]),i[2],(0,255,0),2)

#Code to close Window
cv2.imshow('detected Edge',img1)
cv2.waitKey(0)
cv2.destroyAllWindows()

- Rahul Chougule

---

嗨，SO不是一个“如何”网站，因此您需要编辑此问题并展示您尝试过什么，什么有效或无效，并基于此提出具体问题。 - Kevin Versfeld

我为您使用了谷歌：http://opencvexamples.blogspot.com/2014/02/crop-elliptical-region-from-image.html翻译成Python。 - Piglet

Answer 1

1. 制作口罩：

height,width = img.shape
mask = np.zeros((height,width), np.uint8)

2. 在该掩模上绘制圆圈（将线条粗细设置为-1以填充圆圈）：

circle_img = cv2.circle(mask,(i[0],i[1]),i[2],(255,255,255),thickness=-1)

3. 使用该遮罩复制该图像：

masked_data = cv2.bitwise_and(img1, img1, mask=circle_img)

4. 应用阈值

_,thresh = cv2.threshold(mask,1,255,cv2.THRESH_BINARY)

5. 寻找轮廓

contours = cv2.findContours(thresh,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
x,y,w,h = cv2.boundingRect(contours[0])

6. 裁剪掩蔽数据

crop = masked_data[y:y+h,x:x+w]

将此代码添加到您的代码中

import cv2
import numpy as np

img1 = cv2.imread('amol.jpg')
img = cv2.imread('amol.jpg',0)
gray = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(gray, 50, 255, cv2.THRESH_BINARY)

# Create mask
height,width = img.shape
mask = np.zeros((height,width), np.uint8)

edges = cv2.Canny(thresh, 100, 200)
#cv2.imshow('detected ',gray)
cimg=cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
circles = cv2.HoughCircles(edges, cv2.HOUGH_GRADIENT, 1, 10000, param1 = 50, param2 = 30, minRadius = 0, maxRadius = 0)
for i in circles[0,:]:
    i[2]=i[2]+4
    # Draw on mask
    cv2.circle(mask,(i[0],i[1]),i[2],(255,255,255),thickness=-1)

# Copy that image using that mask
masked_data = cv2.bitwise_and(img1, img1, mask=mask)

# Apply Threshold
_,thresh = cv2.threshold(mask,1,255,cv2.THRESH_BINARY)

# Find Contour
contours = cv2.findContours(thresh,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
x,y,w,h = cv2.boundingRect(contours[0])

# Crop masked_data
crop = masked_data[y:y+h,x:x+w]

#Code to close Window
cv2.imshow('detected Edge',img1)
cv2.imshow('Cropped Eye',crop)
cv2.waitKey(0)
cv2.destroyAllWindows()

使用您的图像得出的结果：

- João Cartucho

---

谢谢，这很有帮助。现在可以提取出圆形部分并使背景透明吗？ - Aditya Bhattacharya