ahsinmemon/asn-face-attendence-system

This is a real-time attendance system that uses a webcam to recognize faces and automatically records who is present. Instead of a teacher calling names or students signing a sheet, the camera detects a face, matches it to a stored reference photo, and logs the attendance in a cloud database. The system works in three steps. First, you run a script that reads reference photos of each student, converts each face into a numerical encoding, and saves all those encodings to a file on disk. Second, you upload each student's information (name, student ID, and other details) to a Firebase Realtime Database, which is Google's cloud database service. Third, you start the main program, which opens the webcam, looks for faces in the live feed, compares each detected face against the stored encodings, and when a match is found, fetches that student's information from Firebase and updates their attendance record with a timestamp. The library that does the actual face comparison is called face_recognition, which is a Python package built on top of a widely used computer vision library called dlib. OpenCV handles the webcam feed and the display overlay. The attendance data lives in Firebase so it is accessible from anywhere, and the project includes a script for uploading the initial student data to the database. Setup requires a Firebase project, a service account key file downloaded from the Firebase console, reference images for each person you want the system to recognize, and the Python dependencies installed via pip. The whole stack runs on a standard laptop or desktop with a webcam. The project was built as a learning exercise from tutorial material, with custom modifications for Firebase integration.