Cropping Circle with Hough Transform using OpenCV Python

Question

I want to crop circle from iris image in following below:

and this is my code for circle detection:

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

gambar = cv2.imread('tes2.jpg',0)
cimg = cv2.cvtColor(gambar,cv2.COLOR_GRAY2BGR)
canny = cv2.Canny(cimg,50,50)

circles = cv2.HoughCircles(canny,cv2.HOUGH_GRADIENT,1,10000,
                    param1=50,param2=30,minRadius=50,maxRadius=200)

circles = np.uint16(np.around(circles))
for i in circles[0,:]:
    # draw the outer circle
    cv2.circle(cimg,(i[0],i[2]),i[2],(0,255,0),2)
    # draw the center of the circle
    cv2.circle(cimg,(i[0],i[2]),2,(0,0,255),3)

plt.imshow(cimg,cmap = 'gray')
plt.show()

but, I don't know how to crop this circle (iris localization). I have been following this code reference Cropping circle from the image using OpenCV python. And this is my code below for crop image:

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

gambar1 =cv2.imread('tes2.jpg') 
gambar = cv2.imread('tes2.jpg',0)
cimg = cv2.cvtColor(gambar,cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(cimg, 50, 255, cv2.THRESH_BINARY)

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

canny = cv2.Canny(thresh,100,200)


gray = cv2.cvtColor(gambar,cv2.COLOR_GRAY2BGR)

circles = cv2.HoughCircles(canny,cv2.HOUGH_GRADIENT,1,10000,
                    param1=50,param2=30,minRadius=0,maxRadius=0)


for i in circles[0,:]:
    cv2.circle(mask,(i[0],i[1]),i[2],(255,255,255),thickness=-1)

masked_data = cv2.bitwise_and(gambar1, gambar1, 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]

plt.imshow(gambar1,cmap = 'gray')
plt.imshow(crop, cmap='gray')
plt.show()

but, when I try this code such as reference above, I get an error like this:

File "C:/Users/zurri/spyder/masktes.py", line 14, in <module>
cimg = cv2.cvtColor(gambar,cv2.COLOR_BGR2GRAY)
error: OpenCV(4.2.0) c:\projects\opencv-python\opencv\modules\imgproc\src\color.simd_helpers.hpp:92: error: (-2:Unspecified error) in function '__cdecl cv::impl::`anonymous-namespace'::CvtHelper<struct cv::impl::`anonymous namespace'::Set<3,4,-1>,struct cv::impl::A0xe227985e::Set<1,-1,-1>,struct cv::impl::A0xe227985e::Set<0,2,5>,2>::CvtHelper(const class cv::_InputArray &,const class cv::_OutputArray &,int)'
Invalid number of channels in input image:
     'VScn::contains(scn)'
 where
     'scn' is 1

anyone can help me to fix this problem? I just want to crop this circle (iris localization) using openCV python, thank you

Answer 1

Explanation

---

findContours method retrieves the contours from the given binary image using Suzuki's algorithm. Contours are useful for shape analysis, object detection and recognition.

The findContour method returns two variables: contours and hierarchy. In the original code you did contours = cv2.findContour(...) in which you combines both contours and hierarchy variables. Therefore you had an error. We simply don't need hieararchy variable, therefore we placed _. So the error was resolved.

Solution

---

Replace the findContours line with the below:

contours, _ = cv2.findContours(thresh,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)

Result: