Facial Recognition Attendance System

Quick Specs

• Accuracy: 95%+ (with good lighting)
• Real-time detection speed
• Can store 1000+ user profiles
• Runs on PC/Raspberry Pi
• Integrates with IoT dashboards

Code Example:

import cv2
import face_recognition
import numpy as np
import csv
from datetime import datetime

video = cv2.VideoCapture(0)
known_image = face_recognition.load_image_file("student.jpg")
known_encoding = face_recognition.face_encodings(known_image)[0]

students = ["Student1"]
attendance = {}

while True:
    ret, frame = video.read()
    rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
    face_locations = face_recognition.face_locations(rgb_frame)
    face_encodings = face_recognition.face_encodings(rgb_frame, face_locations)

    for face_encoding in face_encodings:
        matches = face_recognition.compare_faces([known_encoding], face_encoding)
        if True in matches:
            name = students[0]
            if name not in attendance:
                now = datetime.now()
                current_time = now.strftime("%H:%M:%S")
                attendance[name] = current_time
                with open("Attendance.csv", "a") as f:
                    writer = csv.writer(f)
                    writer.writerow([name, current_time])
            cv2.putText(frame, name, (50,50), cv2.FONT_HERSHEY_SIMPLEX,1,(0,255,0),2)

    cv2.imshow("Attendance", frame)
    if cv2.waitKey(1) & 0xFF == ord("q"):
        break

video.release()
cv2.destroyAllWindows()

Learning Outcomes:

• Understand face detection and recognition process
• Learn how to integrate Python with AI libraries
• Gain hands-on experience with OpenCV
• Build a real-world AI-based application