HandTrack.py

# Import necessary libraries
import math
import cv2
import mediapipe as mp
import time

# Create a hand detector class
class handDetector():
    def __init__(self, mode=False, maxHands=2, modelComplexity=1, detectionCon=0.5, trackCon=0.5):
        self.mode = mode
        self.maxHands = maxHands
        self.modelComplex = modelComplexity
        self.detectionCon = detectionCon
        self.trackCon = trackCon
        self.mpHands = mp.solutions.hands
        self.hands = self.mpHands.Hands(self.mode, self.maxHands, self.modelComplex, self.detectionCon, self.trackCon)
        self.mpDraw = mp.solutions.drawing_utils
        self.tipIds = [4, 8, 12, 16, 20]

    # Function to find and draw hands in the image
    def findHands(self, img, draw=True):
        imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
        self.results = self.hands.process(imgRGB)
        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

    # Function to calculate the distance between two points
    def findDistance(self, p1, p2, img, draw=True, r=15, t=3):
        x1, y1 = self.lmList[p1][1:]
        x2, y2 = self.lmList[p2][1:]
        cx, cy = (x1 + x2) // 2, (y1 + y2) // 2

        if draw:
            cv2.line(img, (x1, y1), (x2, y2), (255, 0, 255), t)
            cv2.circle(img, (x1, y1), r, (255, 0, 255), cv2.FILLED)
            cv2.circle(img, (x2, y2), r, (255, 0, 255), cv2.FILLED)
            cv2.circle(img, (cx, cy), r, (0, 0, 255), cv2.FILLED)
            length = math.hypot(x2 - x1, y2 - y1)

        return length, img, [x1, y1, x2, y2, cx, cy]

    # Function to find hand landmarks and their positions
    def findPosition(self, img, handNo=0, draw=True):
        self.lmlist = []
        if self.results.multi_hand_landmarks:
            myHand = self.results.multi_hand_landmarks[handNo]
            for id, lm in enumerate(myHand.landmark):
                h, w, c = img.shape
                cx, cy = int(lm.x * w), int(lm.y * h)
                self.lmlist.append([id, cx, cy])
        return self.lmlist

    # Function to detect finger positions (up or down)
    def fingersUp(self):
        fingers = []
        if self.lmlist[self.tipIds[0]][2] < self.lmlist[self.tipIds[0] - 1][1]:
            fingers.append(1)
        else:
            fingers.append(0)
        for id in range(1, 5):
            if self.lmlist[self.tipIds[id]][2] < self.lmlist[self.tipIds[id] - 2][2]:
                fingers.append(1)
            else:
                fingers.append(0)
        return fingers

# Main function
def main():
    pTime = 0
    cTime = 0
    cap = cv2.VideoCapture(0)
    detector = handDetector()
    while True:
        success, img = cap.read()
        if not success:
            break
        img = detector.findHands(img)
        lmlist = detector.findPosition(img)
        cTime = time.time()
        fps = 1 / (cTime - pTime)
        pTime = cTime

        # Display frames per second (FPS) on the image
        cv2.putText(img, str(int(fps)), (10, 70), cv2.FONT_HERSHEY_SIMPLEX, 3, (255, 0, 255), 3)

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

if __name__ == "__main__":
    main()

# Close OpenCV windows
cv2.destroyAllWindows()