HandTrackingModule.py

import cv2
import mediapipe as mp
import time

class handDetector():
    def __init__(self, mode = False, maxHands = 2, modelComplexity=1, detectionCon=0.5, trackCon=0.5 ):
        self.mode = mode
        self.maxHands = maxHands
        self.modelComplexity = modelComplexity
        self.detectionCon = detectionCon
        self.trackCon = trackCon

        # create a object from class Hand
        self.mpHands = mp.solutions.hands
        # create a object hand with the default values in this case
        self.hands = self.mpHands.Hands(self.mode, self.maxHands, self.modelComplexity,
                                        self.detectionCon, self.trackCon)
        self.mpDraw = mp.solutions.drawing_utils


    def findHands(self, img, draw=True):

        # send the RGB image to this object (hands)
        imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
        self.results = self.hands.process(imgRGB)

        # extract the information of multiples hands or not
        # print(results.multi_hand_landmarks)
        if self.results.multi_hand_landmarks:
            for handLms in self.results.multi_hand_landmarks:
                if draw:
                    self.mpDraw.draw_landmarks(img, handLms, self.mpHands.HAND_CONNECTIONS)
        return img

    def findPosition(self, img, handNo=0, draw=True):
        # get de lane mark positions
        lmList = []
        if self.results.multi_hand_landmarks:
            myHand = self.results.multi_hand_landmarks[handNo]
            # get de id number of the index, get the finger
            for id, lm in enumerate(myHand.landmark):
                # print(id, lm)
                h, w, c = img.shape
                cx, cy = int(lm.x * w), int(lm.y * h)
                # print(id, cx, cy)
                lmList.append([id, cx, cy])
                if draw:
                # if id == 12:
                # above especifict point, below all the dots
                    cv2.circle(img, (cx, cy), 7, (255, 0, 0), cv2.FILLED)

        return lmList
def main():
    # fps
    pTime = 0  # previous time
    cTime = 0  # current time
    # create a video object
    cap = cv2.VideoCapture(0)
    detector = handDetector()

    while True:
        success, img = cap.read()
        img = detector.findHands(img)
        lmList = detector.findPosition(img)
        if len(lmList) != 0:
            print(lmList[4])
        # making fps
        cTime = time.time()
        fps = 1 / (cTime-pTime)
        pTime = cTime

        # display on the screen img/ var / position / font / color
        cv2.putText(img, str(int(fps)), (10, 70), cv2.FONT_HERSHEY_PLAIN,3,
            (255,0,255),3)

        cv2.imshow('Image', img)
        cv2.waitKey(1)

if __name__ == '__main__':
    main()