app.py

import gradio as gr
import face_recognition
import cv2
import numpy as np
from PIL import Image
import pickle
import firebase_admin
from firebase_admin import credentials
from firebase_admin import db
from firebase_admin import storage

# Initialize Firebase
cred = credentials.Certificate("serviceAccountKey.json")  # Update with your credentials path
firebase_app = firebase_admin.initialize_app(cred, {
    'databaseURL': 'https://faceantendancerealtime-default-rtdb.firebaseio.com/',
    'storageBucket': 'faceantendancerealtime.appspot.com'
})
bucket = storage.bucket()

# Function to download face encodings from Firebase Storage
def download_encodings():
    blob = bucket.blob('EncodeFile.p')
    blob.download_to_filename('EncodeFile.p')
    with open('EncodeFile.p', 'rb') as file:
        return pickle.load(file)

encodeListKnownWithIds = download_encodings()
encodeListKnown, studentsIds = encodeListKnownWithIds

def recognize_face(input_image):
    # Convert PIL Image to numpy array
    img = np.array(input_image)
    img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
    # Detect faces and encode
    face_locations = face_recognition.face_locations(img)
    face_encodings = face_recognition.face_encodings(img, face_locations)
    # Initialize the database reference
    ref = db.reference('Students')
    
    # Recognize faces and fetch data from the database
    results = []
    for face_encoding in face_encodings:
        matches = face_recognition.compare_faces(encodeListKnown, face_encoding)
        name = "Unknown"
        student_info = {}

        face_distances = face_recognition.face_distance(encodeListKnown, face_encoding)
        best_match_index = np.argmin(face_distances)
        if matches[best_match_index]:
            student_id = studentsIds[best_match_index]
            student_info = ref.child(student_id).get()

            if student_info:
                name = student_info['name']
                results.append(student_info)
            else:
                results.append({'name': 'Unknown'})
        
        # Draw rectangles around the faces
        for (top, right, bottom, left), name in zip(face_locations, [student_info.get('name', 'Unknown') for student_info in results]):
            cv2.rectangle(img, (left, top), (right, bottom), (0, 0, 255), 2)
            cv2.putText(img, name, (left + 6, bottom - 6), cv2.FONT_HERSHEY_COMPLEX, 0.5, (255, 255, 255), 1)

    # Convert back to PIL Image
    pil_img = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
    return pil_img, results


# Gradio interface
iface = gr.Interface(
    fn=recognize_face,
    inputs=gr.Image(type="pil"),
    outputs=[gr.Image(type="pil"), gr.JSON(label="Student Information")],
    title="Face Recognition Attendance System",
    description="Upload an image to identify individuals."
)

if __name__ == "__main__":
    iface.launch(debug=True,inline=False)