test_classifier.py

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

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

# Initialize MediaPipe hands module
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)

# Define labels dictionary for gesture mapping
labels_dict = {
    0: 'a', 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: '1', 27: '2', 28: '3', 29: '4', 30: '5', 31: '6', 32: '7', 33: '8', 34: '9', 35: '10'
}


# Attempt to open the camera
cap = cv2.VideoCapture(0)
if not cap.isOpened():
    print("Error: Failed to open camera. Exiting...")
    exit()

# Main loop for processing frames from the camera
while True:
    # Read a frame from the camera
    ret, frame = cap.read()

    # Check if frame retrieval was successful
    if not ret:
        print("Error: Failed to retrieve frame from the camera.")
        continue

    # Convert frame to RGB color space
    frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)

    # Process the frame with MediaPipe hands module
    results = hands.process(frame_rgb)

    # Check if hand landmarks are detected
    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())

        # Extract hand landmarks and normalize data
        data_aux = []
        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
                data_aux.append(x)
                data_aux.append(y)

        # Predict gesture using the trained model
        prediction = model.predict([np.asarray(data_aux)])
        predicted_character = labels_dict[int(prediction[0])]

        # Display predicted gesture on the frame
        cv2.putText(frame, predicted_character, (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2, cv2.LINE_AA)

    # Display the frame
    cv2.imshow('Frame', frame)

    # Check for key press to exit
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

# Release the camera and close all OpenCV windows
cap.release()
cv2.destroyAllWindows()