app.py

import cv2
import streamlit as st
import imutils
import numpy as np
import matplotlib.pyplot as plt
from PIL import Image

# Streamlit page configuration
st.set_page_config(page_title="Real-time Face Detection", layout="wide")

# Title for the Streamlit app
st.title("Real-time Face Detection App")

# Function to display images using matplotlib
def plt_imshow(title, image):
    # Convert the image frame from BGR to RGB color space
    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
    plt.imshow(image)
    plt.title(title)
    plt.axis('off')
    st.pyplot(plt)

# Upload the image
uploaded_file = st.file_uploader("Upload an Image", type=["jpg", "png", "jpeg"])

if uploaded_file is not None:
    # Read the uploaded image
    image = Image.open(uploaded_file)
    image = np.array(image)
    
    # Load the Haar Cascade face detector
    cascade_path = "haarcascade_frontalface_default.xml"
    detector = cv2.CascadeClassifier(cascade_path)

    # Convert the image to grayscale
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

    # Perform face detection
    rects = detector.detectMultiScale(gray, scaleFactor=1.05, minNeighbors=5, minSize=(30, 30), flags=cv2.CASCADE_SCALE_IMAGE)

    # Draw bounding boxes around detected faces
    for (x, y, w, h) in rects:
        cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2)

    # Display the result in Streamlit
    st.image(image, caption="Face Detected", channels="BGR", use_column_width=True)

# Upload video file
uploaded_video = st.file_uploader("Upload a Video", type=["mp4", "avi"])

if uploaded_video is not None:
    # Open the uploaded video
    video_file = uploaded_video.read()
    
    # Use OpenCV to read the video
    video_capture = cv2.VideoCapture(video_file)

    # Load the Haar Cascade face detector
    cascade_path = "haarcascade_frontalface_default.xml"
    detector = cv2.CascadeClassifier(cascade_path)

    # Create a video writer to save the output video
    fourcc = cv2.VideoWriter_fourcc(*"MJPG")
    output_file = "output_video.avi"
    writer = cv2.VideoWriter(output_file, fourcc, 20, (640, 480))

    while video_capture.isOpened():
        ret, frame = video_capture.read()
        if not ret:
            break

        # Resize and convert the frame to grayscale
        frame = imutils.resize(frame, width=500)
        gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

        # Perform face detection
        rects = detector.detectMultiScale(gray, scaleFactor=1.05, minNeighbors=5, minSize=(30, 30), flags=cv2.CASCADE_SCALE_IMAGE)

        # Draw bounding boxes around detected faces
        for (x, y, w, h) in rects:
            cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)

        # Write the processed frame to the output video
        writer.write(frame)

    # Release the video capture and writer objects
    video_capture.release()
    writer.release()

    # Show the output video in Streamlit
    st.video(output_file)