How to detect edge points of an object using OpenCV Python?

Question

So, I have already detected all the edges of an object but the problem is that I can't find the two points of each edge, that is, the starting point and the ending point with its coordinates.

Actually I am trying to find the measurements of an object but I am stuck at this problem.The image is regarding the ROI of the image.

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

#Read Image of the Object
img = cv2.imread("C:\\Users\\Desktop\\Project\\captured.jpg")
cv2.imshow('Original Image', img)
cv2.waitKey(0)



#Convert Image To GrayScale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
cv2.imshow('Gray', gray)
cv2.waitKey(0)


#Binary Thresholding
ret, thresh = cv2.threshold(gray, 150, 255, cv2.THRESH_BINARY_INV)
cv2.imshow('Binary Image', thresh)
cv2.waitKey(0)

#Crop Image
cropped = thresh[150:640, 150:500]
cv2.imshow('Cropped Image', cropped)
cv2.waitKey(0)

#Edge Detection
edges = cv2.Canny(cropped, 100, 200)
cv2.imshow('Edges', edges)
cv2.waitKey(0)

#find contours
ctrs, hier = cv2.findContours(cropped, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)

#Sort Contours
sorted_ctrs = sorted(ctrs, key=lambda ctr: cv2.boundingRect(ctr)[0] + cv2.boundingRect(ctr)[1] * cropped.shape[1])


#ROI
for i, ctr in enumerate(sorted_ctrs):
    # Get bounding box
    x, y, w, h = cv2.boundingRect(ctr)

    # Getting ROI
    roi = cropped[y:y + h, x:x + w]
    # show ROI
    # cv2.imshow('segment no:'+str(i),roi)
    cv2.rectangle(cropped , (x, y), (x + w, y + h), (150, 0, 255), 2)
cv2.imshow('marked areas', cropped)
cv2.waitKey(0)

Original Image

These are 5 points and the five edges that I need with coordinates so I can calculate the distance between them for the measurement.

Harris Corner Output.

Can you attach sample input image along with expected output ? — ZdaR
– ZdaR, Commented Feb 8, 2019 at 9:47
I have edited the question with the changes. Can you look at it now? — Jimit Vaghela
– Jimit Vaghela, Commented Feb 8, 2019 at 9:55
@JimitVaghela hii i have calculated the edge length of sides of image. Now, i want to know how to know represent it like imgur.com/a/e2CVGxA any idea how to achieve this — k_p
– k_p, Commented Jun 26, 2021 at 7:47

Rick M. · Accepted Answer · 2019-02-08 10:55:58Z

1

Try using Harris Corner Detection instead:

import cv2
import numpy as np

def find_centroids(dst):
    ret, dst = cv2.threshold(dst, 0.01 * dst.max(), 255, 0)
    dst = np.uint8(dst)

    # find centroids
    ret, labels, stats, centroids = cv2.connectedComponentsWithStats(dst)
    # define the criteria to stop and refine the corners
    criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 100, 
                0.001)
    corners = cv2.cornerSubPix(gray,np.float32(centroids),(5,5), 
              (-1,-1),criteria)
    return corners

image = cv2.imread("corner.jpg")
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

gray = np.float32(gray)

dst = cv2.cornerHarris(gray, 2, 3, 0.04)

dst = cv2.dilate(dst, None)

# Threshold for an optimal value, it may vary depending on the image.
# image[dst > 0.01*dst.max()] = [0, 0, 255]

# Get coordinates
corners= find_centroids(dst)
# To draw the corners
for corner in corners:
    image[int(corner[1]), int(corner[0])] = [0, 0, 255]
cv2.imshow('dst', image)
cv2.waitKey(0)
cv2.destroyAllWindows()

Result:

You might need to fine tune the parameters for cornerHarris.

edited Feb 8, 2019 at 10:55

answered Feb 8, 2019 at 10:04

Rick M.

3,1451 gold badge25 silver badges39 bronze badges

Sign up to request clarification or add additional context in comments.

14 Comments

Jimit Vaghela Over a year ago

Thank you for responding. Can I actually store these point values to a variable so I can use them to calculate the distance between them?

Rick M. Over a year ago

Yes you can. Just edited the answer. They are just close estimates to the found corners since it find multiple corners at the same corner

Jimit Vaghela Over a year ago

Also, the suggestion you have provided is giving me an error: IndexError: boolean index did not match indexed array along dimension 0; dimension is 330 but corresponding boolean dimension is 480

Rick M. Over a year ago

I have tried the code and it works. What error are you getting?

Jimit Vaghela Over a year ago

At line 32 : NameError: name 'corners' is not defined I am having this error.

|

Collectives™ on Stack Overflow

How to detect edge points of an object using OpenCV Python?

1 Answer 1

14 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

14 Comments

Your Answer

Sign up or log in

Post as a guest

Related