Language.py

import pickle
from ultralytics import YOLO
import cv2
import mediapipe as mp
import numpy as np



model = YOLO('best.pt')

cap = cv2.VideoCapture(0)

mp_hands = mp.solutions.hands
mp_drawing = mp.solutions.drawing_utils
mp_drawing_styles = mp.solutions.drawing_styles

hands = mp_hands.Hands(static_image_mode=True, min_detection_confidence=0.3)
language = ''
labels_dict = {0: '0', 1: 'B', 2: 'C', 3: 'D', 4: 'E', 5: 'F', 6: 'G', 7: 'H', 8: 'I', 9: 'J', 10: 'K', 11: 'L', 12: 'M', 13: 'N', 14: 'O', 15: 'P', 16: 'Q', 17: 'R', 18: 'S', 19: 'T', 20: 'U', 21: 'V', 22: 'W', 23: 'X', 24: 'Y', 25: 'Z', 26: 'del', 27: 'nothing', 28: 'space'}
while True:

    data_aux = []
    x_ = []
    y_ = []
    

    ret, frame = cap.read()
    if not ret:
        print("Failed to capture frame. Exiting...")
        break    

    H, W, _ = frame.shape

    frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)

    results = hands.process(frame_rgb)
    if results.multi_hand_landmarks:
        for hand_landmarks in results.multi_hand_landmarks:
            mp_drawing.draw_landmarks(
                frame, 
                hand_landmarks,  
                mp_hands.HAND_CONNECTIONS,  
                mp_drawing_styles.get_default_hand_landmarks_style(),
                mp_drawing_styles.get_default_hand_connections_style())

        for hand_landmarks in results.multi_hand_landmarks:
            for i in range(len(hand_landmarks.landmark)):
                x = hand_landmarks.landmark[i].x
                y = hand_landmarks.landmark[i].y

                x_.append(x)
                y_.append(y)

            for i in range(len(hand_landmarks.landmark)):
                x = hand_landmarks.landmark[i].x
                y = hand_landmarks.landmark[i].y
                data_aux.append(x - min(x_))
                data_aux.append(y - min(y_))

        x1 = int(min(x_) * W) - 10
        y1 = int(min(y_) * H) - 10

        x2 = int(max(x_) * W) - 10
        y2 = int(max(y_) * H) - 10
       
        prediction = model.predict(frame, conf=0.25, iou=0.45)
        names_dict = prediction[0].names
        probs = prediction[0].probs.data.numpy()
        detected_gesture = names_dict[np.argmax(probs)]
        print(names_dict[np.argmax(probs)])
        print("Gesture:", detected_gesture)
        if detected_gesture == 'A':
            language = 'Arabic'
        elif detected_gesture == 'B':
            language = 'Bengali'
        elif detected_gesture == 'C':
            language = 'Chinese'
        elif detected_gesture == 'D':
            language = 'Dutch'
        elif detected_gesture == 'E':
            language = 'English'
        elif detected_gesture == 'F':
            language = 'French'
        elif detected_gesture == 'G':
            language = 'German'
        elif detected_gesture == 'H':
            language = 'Hindi'
        elif detected_gesture == 'I':
            language = 'Italian'
        elif detected_gesture == 'J':
            language = 'Japanese'
        elif detected_gesture == 'K':
            language = 'Korean'
        elif detected_gesture == 'L':
            language = 'Latin'
        elif detected_gesture == 'M':
            language = 'Malay'
        elif detected_gesture == 'N':
            language = 'Norwegian'
        elif detected_gesture == 'O':
            language = 'Oriya'
        elif detected_gesture == 'P':
            language = 'Polish'
        elif detected_gesture == 'Q':
            language = 'Quechua'
        elif detected_gesture == 'R':
            language = 'Russian'
        elif detected_gesture == 'S':
            language = 'Spanish'
        elif detected_gesture == 'T':
            language = 'Turkish'
        elif detected_gesture == 'U':
            language = 'Urdu'
        elif detected_gesture == 'V':
            language = 'Vietnamese'
        elif detected_gesture == 'W':
            language = 'Welsh'
        elif detected_gesture == 'X':
            language = 'Xhosa'
        elif detected_gesture == 'Y':
            language = 'Yoruba'
        elif detected_gesture == 'Z':
            language = 'Zulu'


        cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 0, 0), 4)
        cv2.putText(frame, language, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 1.3, (0, 0, 0), 3,
                    cv2.LINE_AA)

    cv2.imshow('frame', frame)
    cv2.waitKey(1)


cap.release()
cv2.destroyAllWindows()