CODEWITHSUNDEEP
pythonnumpyopencvimage-processing
Gkisi27
Gkisi27

Reputation: 177

How to detect the specific coordinate points from array of points given by corner detection?

I have an image of a person head from which I detected the corner points. Here are my code and result from it:

import cv2
import numpy as np

Head = cv2.imread('Head.jpg')

#Corner detection
gray = cv2.cvtColor(Head, cv2.COLOR_BGR2GRAY)
gray  = np.float32(gray)

corners = cv2.goodFeaturesToTrack(gray, 50, 0.01, 10)
corners = np.int0(corners)

for corner in corners:
    x,y = corner.ravel()
    cv2.circle(Head, (x,y), 3, 255, -1)

z = np.max(y)
cv2.circle(Head, (x,z), 5, (0,0,255), -1)

cv2.imshow('Corner', Head)
cv2.waitKey(0)
cv2.destroyAllWindows()

Head Image:

Head.jpg

Corner Detected:

Corner Points

Here, I am trying to point out only two corners in neck area(Lowest ones in above image). For that, I find out the max y from numpy array of corners and plot the point in red point. But, its plotting red point in eye. What I am doing wrong?

How do I find out the coordinate points of neck(lowest 2 corner points only)??

Upvotes: 0

Views: 711

Answers (1)

westgarthw
westgarthw

Reputation: 181

The issue is in this line:

z = np.max(y)

Here the value of y will just be the value of the last corner looked at in the previous loop. What you can do is to create a list of all the coordinate of the corners, and then order the list based on the y value:

ordered_coords = [ corner.ravel() for corner in corners ]
ordered_coords.sort(key=lambda x: x[1])

The two corners you're looking for with the highest y value will then be the last two elements in the list.

cv2.circle(Head, ordered_coords[-1], 5, (0,0,255), -1)

Upvotes: 1

Related Questions