app.py

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

# Create a Streamlit app
st.title("Face Detection and Image Capture")
Name = st.text_input('Enter Your Name:')

# Load the Haar Cascade Classifier for face detection
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')

# Initialize the webcam
cap = cv2.VideoCapture(0)
cap.set(3, 640)
cap.set(4, 480)

# Define the directory where images will be saved
save_dir = "images"

# Function to detect faces and draw rectangles
def detect_faces(image):
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=5)
    for (x, y, w, h) in faces:
        cv2.rectangle(image, (x, y), (x + w, y + h), (255, 0, 0), 2)
    return image

# Capture an image from the camera
image_file = st.camera_input("Take a picture")

# Display the captured image and perform face detection
if image_file:
    try:
        # Convert the image to a valid PIL Image
        pil_image = Image.open(image_file)

        # Convert PIL Image to NumPy array
        image_np = np.array(pil_image)

        # Read the image using OpenCV
        image_with_faces = detect_faces(image_np)

        # Convert the BGR image to RGB
        rgb_image = cv2.cvtColor(image_with_faces, cv2.COLOR_BGR2RGB)
        
        st.image(rgb_image, channels="RGB", use_column_width=True)
        
        # Define the path to save the image
        image_filename = f"{Name}.jpg"
        image_path = os.path.join(save_dir + image_filename)
        
        # Save the image locally in RGB format
        cv2.imwrite(image_path, cv2.cvtColor(rgb_image, cv2.COLOR_RGB2BGR))
        
        st.success(f"Image saved as {image_path}")
    except Exception as e:
        st.error(f"Error saving image: {str(e)}")

# Release the webcam when the app is done
cap.release()