import cv2
import streamlit as st
import numpy as np
from PIL import Image
import time

# Load the pre-trained Haar Cascade face detector
face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')

# Define a function to detect faces in a frame
def detect_faces(frame):
    # Convert the frame to grayscale (Haar Cascade works on grayscale images)
    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

    # Detect faces in the image
    faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=5, minSize=(30, 30))

    # Draw rectangles around the faces
    for (x, y, w, h) in faces:
        cv2.rectangle(frame, (x, y), (x + w, y + h), (255, 0, 0), 2)

    return frame

# Streamlit UI for the app
st.title("Real-Time Face Detection")

# Create a container for the webcam video feed
video_placeholder = st.empty()

# Start the webcam feed
cap = cv2.VideoCapture(0)  # 0 is the default webcam device

if not cap.isOpened():
    st.error("Error: Could not access the webcam.")
else:
    # Start capturing video frames
    while True:
        ret, frame = cap.read()

        if not ret:
            st.error("Failed to grab frame.")
            break

        # Detect faces in the current frame
        result_frame = detect_faces(frame)

        # Convert BGR (OpenCV format) to RGB (for Streamlit display)
        result_frame_rgb = cv2.cvtColor(result_frame, cv2.COLOR_BGR2RGB)

        # Display the frame in Streamlit (dynamically updating the image)
        video_placeholder.image(result_frame_rgb, channels="RGB", use_column_width=True)

        # Add a small delay to control the frame rate (optional)
        time.sleep(0.03)  # This gives roughly 30 FPS

# Release the webcam when the stream ends
cap.release()