Sign-Language-Prediction/inference_classifier.py at main · vijayrajeshr/Sign-Language-Prediction · GitHub

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
import pickle
import cv2
import mediapipe as mp
import numpy as np

model_dict = pickle.load(open('./model.p', 'rb'))
model = model_dict['model']

camera_indices = [0,1,2]
cap = None
for index in camera_indices:
    cap = cv2.VideoCapture(index)
    if cap.isOpened():
        print(f"Using camera index {index}")
        break
else:
    print("No camera found")
    exit()

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)


labels_dict = {i: chr(65 + i) for i in range(26)}

while True:
    data_aux = []
    x_ = []
    y_ = []

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


        while len(data_aux) < 84:
            data_aux.extend([0, 0])
        data_aux = data_aux[:84]

        prediction = model.predict([np.asarray(data_aux)])
        predicted_character = prediction[0]

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

    cv2.imshow('frame', frame)
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

cap.release()
cv2.destroyAllWindows()