CODEWITHSUNDEEP
pythonpython-3.xopencvimage-morphologyimage-thresholding
hawxeye
hawxeye

Reputation: 99

How to remove white pixels that are not connected to a loop in binary image

I have a image which I have binarized and the problem is I want to remove the white spots in that image which are not connected in a loop i.e. small white dots. The reason is I want to take a measurement of that section like shown here.

I have tried some OpenCV morphology functions like erode, open, close but the results are not what I require. I have also tried using canny edge but some diagonal lines which I want for some processing are also gone. here is the result of both thresh(left) and canny(right)

I have read that pruning is a process in which we remove pixels which are not connected but I don't know how it works? Is there a function in Opencv for that?

th3 = cv2.adaptiveThreshold(gray_img,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C,cv2.THRESH_BINARY,11,2)
th3=~th3
th3 = cv2.dilate(th3, cv2.getStructuringElement(cv2.MORPH_RECT,(3,3)))
th3 = cv2.erode(th3, cv2.getStructuringElement(cv2.MORPH_RECT,(5,5)))
edged = cv2.Canny(gray_img,lower,upper)

Upvotes: 3

Views: 671

Answers (1)

Stephen Meschke
Stephen Meschke

Reputation: 2940

This answer explains how to measure the diameter of the drill bit:

The first step is to read the image as 2 channel (grayscale) and find the edges using a Canny filter:

img = cv2.imread('/home/stephen/Desktop/drill.jpg',0)
canny = cv2.Canny(img, 100, 100)

canny

The edges of the drill using np.argmax():

diameters = []
# Iterate through each column in the image
for row in range(img.shape[1]-1):
    img_row = img[:, row:row+1]
    start = np.argmax(img_row)
    end = np.argmax(np.flip(img_row))
    diameters.append(end+start)
    a = row, 0
    b = row, start
    c = row, img.shape[1]
    d = row, img.shape[0] - end
    cv2.line(img, a, b, 123, 1)
    cv2.line(img, c, d, 123, 1)

outline

The diameter of the drill in each column is plotted here:

diameters

All of this assumes that you have an aligned image. I used this code to align the image.

Upvotes: 2

Related Questions