Spaces:
Runtime error
Runtime error
| import streamlit as st | |
| from utils.levels import complete_level, render_page, initialize_level | |
| from utils.login import initialize_login | |
| import cv2 | |
| LEVEL = 1 | |
| initialize_login() | |
| initialize_level() | |
| def returnCameraIndexes(): | |
| # checks the first 10 indexes. | |
| index = 0 | |
| arr = [] | |
| i = 10 | |
| while i > 0: | |
| cap = cv2.VideoCapture(index) | |
| if cap.read()[0]: | |
| arr.append(index) | |
| cap.release() | |
| index += 1 | |
| i -= 1 | |
| return arr | |
| def step1_page(): | |
| st.header("Technology Behind It") | |
| st.markdown( | |
| """ | |
| ### How does it work? | |
| In this tutorial, we will explore the fascinating world of face recognition technology. Through this interactive web application, | |
| you will learn the fundamentals of face detection, feature encodings, and face recognition algorithms. | |
| Throughout the tutorial, you will have the opportunity to upload images and experience the power of face recognition firsthand. | |
| Step by step, we will guide you through the process, ensuring that you gain a deep understanding of each concept and its practical implementation. | |
| Here's how it works: | |
| 1. **Face Detection**: In this first step, discover how face detection algorithms locate and identify faces within an image. | |
| You will see how this crucial first step sets the foundation for subsequent face recognition tasks. | |
| 2. **Face Encodings**: Next, the application pays attention to learn about face encodings, a technique that extracts unique | |
| facial characteristics and represents them as numerical vectors. These features capture unique characteristics that enable reliable comparisons between faces. | |
| Here we will generate face encodings for the known faces to create a data base. | |
| 3. **Face Recognition**: Dive into the world of face recognition algorithms, where you will understand the mechanisms | |
| behind comparing face encodings and making accurate matches. It uses the face encoding of unknown face against the face encodings of known faces to compare and find matching features. | |
| """ | |
| ) | |
| st.image( | |
| "https://user-images.githubusercontent.com/31125521/41526995-1a90e4e6-72e6-11e8-96d4-8b2ccdee5f79.gif", | |
| use_column_width=True, | |
| ) | |
| st.markdown( | |
| """ | |
| So, our face recognition model is like a clever brain that looks at faces, notices important features, and identifies the person by name if it already knows their name. | |
| It's a way for computers to recognize faces, just like we do as humans! | |
| """ | |
| ) | |
| st.info("Click on the button below to continue!") | |
| """TEST""" | |
| input_type = st.radio("Select the Input Type", ["Image upload", "Camera", "Live Video"]) | |
| st.write(returnCameraIndexes()) | |
| if input_type == "Live Video": | |
| cam = cv2.VideoCapture(0) | |
| if not cam.isOpened(): | |
| print("Cannot open camera") | |
| exit() | |
| cam.set(cv2.CAP_PROP_FRAME_WIDTH, 640) | |
| cam.set(cv2.CAP_PROP_FRAME_HEIGHT, 480) | |
| FRAME_WINDOW = st.image([]) | |
| while True: | |
| ret, frame = cam.read() | |
| if not ret: | |
| st.error("Failed to capture frame from camera") | |
| st.info("Please turn off the other app that is using the camera and restart app") | |
| st.stop() | |
| # image, name, face_id = recognize(frame, tolerance) | |
| image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB) | |
| # Display name and ID of the person | |
| FRAME_WINDOW.image(image) | |
| if st.button("Complete"): | |
| complete_level(LEVEL) | |
| render_page(step1_page, LEVEL) | |