Creating a Finger Counter Using Computer Vision and OpenCv in Python

In this article, we are going to create a finger counter using Computer Vision, OpenCv in Python

Required Libraries:

• OpenCV: OpenCV is a widely used library for image processing.
• cvzone: It is a computer vision package that makes it easy to run Image processing and AI functions

To install the Cvzone, run this command into terminal:

pip install cvzone

Stepwise Implementation:

Step 1: Import required libraries.

Python3

# import libraries and required classes
import cv2
from cvzone.HandTrackingModule import HandDetector

Step 2: Declare the HandDetector and open the default camera to capture the hand.

Python3

# declaring HandDetector with
# some basic requirements
detector = HandDetector(maxHands=1,
                        detectionCon=0.8)

# it detect only one hand from
# video with 0.8 detection confidence
video = cv2.VideoCapture(0)

Step 3: Count the number of fingers

Capture the frames continuously and detect the hand from the frame then detect how many fingers are up and count them. On the counter make appropriate conditions and place an image of fingers.

Python3

while True:
      # Capture frame-by-frame
    _, img = video.read()
    img = cv2.flip(img, 1)

    # Find the hand with help of detector
    hand = detector.findHands(img, draw=False)

    # Here we take img by default if no hand found
    fing = cv2.imread("Put image path with 0 fingures up")
    if hand:

          # Taking the landmarks of hand
        lmlist = hand[0]
        if lmlist:

              # Find how many fingers are up
            # This function return list
            fingerup = detector.fingersUp(lmlist)

            # Change image based on
            # different-different conditions
            if fingerup == [0, 1, 0, 0, 0]:
                fing = cv2.imread("Put image path of 1\
                fingures up")
            if fingerup == [0, 1, 1, 0, 0]:
                fing = cv2.imread("Put image path of 2\
                fingures up")
            if fingerup == [0, 1, 1, 1, 0]:
                fing = cv2.imread("Put image path of\
                3 fingures up")
            if fingerup == [0, 1, 1, 1, 1]:
                fing = cv2.imread("sPut image path \
                of 4 fingures up")
            if fingerup == [1, 1, 1, 1, 1]:
                fing = cv2.imread("Put image path \
                of 4 fingures and thumbs up")
    # Resize the image
    fing = cv2.resize(fing, (220, 280))

    # Place the image in main frame
    img[50:330, 20:240] = fing

    # Display the resulting frame
    cv2.imshow("Video", img)

How actually detector detects the fingers up or down.

• It returns the list of five elements and each element depends on the finger’s condition. 
• The list order like [ thumb, index finger, middle finger, ring finger, pinky/little finger ]
• If any of the fingers are up, it returns 1 for that particular index value else returns 0.
• And after making the list it will return by the function.

Step 4: Terminate the loop 

Python3

# Enter key 'q' to break the loop
if cv2.waitKey(1) & 0xFF == ord('q'):
    break

# When everything done, release
# the capture and destroy the windows
video.release()
cv2.destroyAllWindows()

Below is the complete implementation:

Python3

import cv2
from cvzone.HandTrackingModule import HandDetector

detector = HandDetector(maxHands=1, detectionCon=0.8)
video = cv2.VideoCapture(1)

while True:
    _, img = video.read()
    img = cv2.flip(img, 1)
    hand = detector.findHands(img, draw=False)
    fing = cv2.imread("Put image path with 0 fingures up")
    if hand:
        lmlist = hand[0]
        if lmlist:
            fingerup = detector.fingersUp(lmlist)
            if fingerup == [0, 1, 0, 0, 0]:
                fing = cv2.imread("Put image \
                path of 1 fingures up")
            if fingerup == [0, 1, 1, 0, 0]:
                fing = cv2.imread("Put image \
                path of 2 fingures up")
            if fingerup == [0, 1, 1, 1, 0]:
                fing = cv2.imread("Put image \
                path of 3 fingures up")
            if fingerup == [0, 1, 1, 1, 1]:
                fing = cv2.imread("Put image \
                path of 4 fingures up")
            if fingerup == [1, 1, 1, 1, 1]:
                fing = cv2.imread("Put image \
                path of 4 fingures and thumbs up")
    fing = cv2.resize(fing, (220, 280))
    img[50:330, 20:240] = fing
    cv2.imshow("Video", img)

    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

video.release()
cv2.destroyAllWindows()

Output :