Spaces:
Runtime error
Runtime error
File size: 4,399 Bytes
43317b5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 |
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()
|