[Python] Why does the variance result exceed 0 when using the TM_SQDIFF method to match an...

My code looks like this:

import numpy as np
import cv2

print(f'cv2_version:{cv2.__version__}')
test_image = cv2.imread('LIDjQLdr.jpg')
test_gray_image = cv2.cvtColor(test_image , cv2.COLOR_BGR2GRAY)

result = cv2.matchTemplate(test_gray_image, test_gray_image, cv2.TM_SQDIFF)
min_val, _, min_loc, _ = cv2.minMaxLoc(result)
print("min_val:", min_val)
print("min_loc:", min_loc)


This is the test image:



Result:

cv2_version:4.5.4

min_val: 160.0

min_loc: (0, 0)


Why is the min_val greater than 0 when it should be zero?

Continue reading...