How to detect bullet holes on the target

Question

I want to know how to detect the bullet holes on the target using Python and OpenCV.

I'm not able to draw the contours around them. So far I have applied a threshold, and I have the following result (Image after threshold and binary AND):

And here's the original image:

I don't know which approach I should follow to detect the bullet holes and calculate the scores accordingly.

Answer 1

You may simply use a very simple type of segmentation technique, known as Color Segmentation in which you threshold the given RGB image to get a binary image as :

img = cv2.imread('/Users/anmoluppal/Desktop/cAMDX.jpg')

img_thresholded = cv2.inRange(img, (60, 60, 60), (140, 140, 140))

The noise of the binary image can be removed using the opening operation on the binary image as :

kernel = np.ones((10,10),np.uint8)
opening = cv2.morphologyEx(img_thresholded, cv2.MORPH_OPEN, kernel)

Now you have somewhat a clear picture of the bullet holes, the last part is to find these contours and draw some circle/ Rectangle around them to highlight the foreground area as:

contours, hierarchy = cv2.findContours(opening.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
print len(contours)

for contour in contours:
    (x,y),radius = cv2.minEnclosingCircle(contour)
    center = (int(x),int(y))
    radius = int(radius)
    cv2.circle(img,center,radius,(0,255,0),2)
    # labelling the circles around the centers, in no particular order.
    position = (center[0] - 10, center[1] + 10)
    text_color = (0, 0, 255)
    cv2.putText(img, str(i + 1), position, cv2.FONT_HERSHEY_SIMPLEX, 1, text_color, 3)