SmartPicasso/gestures/gesture_recognition.py

import cv2
import mediapipe as mp

mp_drawing = mp.solutions.drawing_utils
mp_hands = mp.solutions.hands
from math import sqrt


def calculate_distance(ax, ay, bx, by):
    distance = sqrt(((bx - ax) ** 2 + (by - ay) ** 2))
    return distance


hands = mp_hands.Hands(
    min_detection_confidence=0.5, min_tracking_confidence=0.5)
cap = cv2.VideoCapture(0)
while cap.isOpened():
    success, image = cap.read()

    # Flip the image horizontally for a later selfie-view display, and convert
    # the BGR image to RGB.
    image = cv2.cvtColor(cv2.flip(image, 1), cv2.COLOR_BGR2RGB)
    # To improve performance, optionally mark the image as not writeable to
    # pass by reference.
    image.flags.writeable = False
    results = hands.process(image)

    # Draw the hand annotations on the image.g
    image.flags.writeable = True
    image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
    if results.multi_hand_landmarks:
        for hand_landmarks in results.multi_hand_landmarks:
            mp_drawing.draw_landmarks(
                image, hand_landmarks, mp_hands.HAND_CONNECTIONS)
            # print(hand_landmarks)        ## spójrz na to
    if cv2.waitKey(33) == ord('s'):
        if results.multi_hand_landmarks:
            i = 0
            for hand_landmarks in results.multi_hand_landmarks:
                ax = hand_landmarks.landmark[8].x
                ay = hand_landmarks.landmark[8].y
                bx = hand_landmarks.landmark[5].x
                by = hand_landmarks.landmark[5].y
                distance_8_5 = calculate_distance(ax, ay, bx, by)
                print(distance_8_5)
                ax = hand_landmarks.landmark[5].x
                ay = hand_landmarks.landmark[5].y
                bx = hand_landmarks.landmark[0].x
                by = hand_landmarks.landmark[0].y
                distance_5_0 = calculate_distance(ax, ay, bx, by)
                print(distance_5_0)
                if (distance_5_0 < distance_8_5 + 0.1):
                    print("wyprostowany")
                else:
                    print("niewyprostowany")

                # i += 1
                # print(hand_landmarks.)

    cv2.imshow('MediaPipe Hands', image)
    if cv2.waitKey(5) & 0xFF == 27:
        break
hands.close()
cap.release()