Spaces:
Runtime error
Runtime error
| import cv2 | |
| import mediapipe as mp | |
| import numpy as np | |
| import tensorflow as tf | |
| import gradio as gr | |
| # Load pre-trained model (replace 'model.h5' with the actual model path) | |
| model = tf.keras.models.load_model("sign_language_model.h5") | |
| # MediaPipe Hands setup | |
| mp_hands = mp.solutions.hands | |
| mp_drawing = mp.solutions.drawing_utils | |
| # Define labels (replace with your model's classes) | |
| labels = ["A", "B", "C", "D", "E"] # Example labels | |
| # Process webcam frame and predict sign language gesture | |
| def recognize_sign(image): | |
| # Convert the input image to RGB | |
| rgb_image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) | |
| # MediaPipe Hand Detection | |
| with mp_hands.Hands(static_image_mode=False, | |
| max_num_hands=1, | |
| min_detection_confidence=0.7, | |
| min_tracking_confidence=0.7) as hands: | |
| result = hands.process(rgb_image) | |
| if result.multi_hand_landmarks: | |
| for hand_landmarks in result.multi_hand_landmarks: | |
| # Draw landmarks on the image | |
| mp_drawing.draw_landmarks(image, hand_landmarks, mp_hands.HAND_CONNECTIONS) | |
| # Extract hand landmark coordinates as features | |
| landmarks = [] | |
| for lm in hand_landmarks.landmark: | |
| landmarks.extend([lm.x, lm.y, lm.z]) | |
| # Reshape data for prediction | |
| features = np.array(landmarks).reshape(1, -1) | |
| # Predict gesture | |
| prediction = model.predict(features) | |
| gesture = labels[np.argmax(prediction)] | |
| # Display the predicted gesture on the image | |
| h, w, _ = image.shape | |
| cv2.putText(image, gesture, (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2) | |
| return gesture, image | |
| return "No hand detected", image | |
| # Gradio interface wrapper | |
| def gradio_wrapper(image): | |
| # Convert Gradio input to OpenCV format | |
| image = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR) | |
| gesture, annotated_image = recognize_sign(image) | |
| # Convert the annotated image back to RGB for display | |
| annotated_image = cv2.cvtColor(annotated_image, cv2.COLOR_BGR2RGB) | |
| return gesture, annotated_image | |
| # Create Gradio Interface | |
| interface = gr.Interface( | |
| fn=gradio_wrapper, | |
| inputs=gr.inputs.Image(source="webcam", tool=None), | |
| outputs=[gr.outputs.Textbox(label="Predicted Gesture"), | |
| gr.outputs.Image(label="Annotated Image")], | |
| live=True, | |
| title="Sign Language Recognition", | |
| description="Predicts sign language gestures using TensorFlow and MediaPipe." | |
| ) | |
| # Launch the Gradio app | |
| if __name__ == "__main__": | |
| interface.launch() | |