For black images you get the total number of pixels (rows*cols) and then subtract it from the result you get from cv2.countNonZero(mat)
.
For other values, you can create a mask using cv2.inRange()
to return a binary mask showing all the locations of the color/label/value you want and then use cv2.countNonZero
to count how many of them there are.
UPDATE (Per Miki’s comment):
When trying to find the count of elements with a particular value, Python allows you to skip the cv2.inRange()
call and just do:
cv2.countNonZero(img == scalar_value)