Face Recognition Attendance System

Desktop app that marks student attendance automatically by recognising faces through the webcam, with subject-wise reports and attendance percentage.

  • Price: ₹1,999
  • Category: AI / ML
  • Technology: Python, Tkinter, OpenCV, LBPH Face Recognizer, Haar Cascade, SQLite
  • Includes: Source code + database
  • Suitable for: BCA / B.Sc CS, MCA / M.Sc CS, B.E / B.Tech CSE & IT

Project overview

A computer-vision desktop application that replaces the paper attendance register. The admin registers each student once (enrollment number, name, department, year) and the app captures 40 face samples through the laptop webcam. A Local Binary Patterns Histogram (LBPH) face recogniser is trained on these samples. It was chosen because it works on a normal laptop CPU, needs no GPU or internet, and handles changes in lighting well. During class the faculty picks the subject and starts the camera: every recognised face is marked present instantly, and unknown faces are shown in red and never marked. Each student can be marked only once per subject per day, so duplicates are impossible. A manual attendance screen is included for days when the camera is not available. The Reports screen filters attendance by subject, date range or student, calculates each student's attendance percentage, and exports any view to CSV (opens in Excel). Everything is stored in a local SQLite database, so there is no XAMPP/MySQL setup. In testing, the model recognised 31 of 31 unseen face images correctly and rejected random non-face input.

Modules

  1. Admin login: Secure login with a hashed password. The password can be changed from Settings.
  2. Dashboard: Shows the number of registered students, subjects and students present today, plus model status and quick-start steps.
  3. Student registration & face capture: Add, search and delete students. Captures 40 face samples from the webcam, saved only when exactly one face is visible.
  4. Model training: Trains the LBPH face recogniser on all saved face samples with one click, and reports how many students and images were used.
  5. Face attendance: Live webcam recognition for the chosen subject. Recognised students are marked present with the time, and unknown faces are ignored. No duplicate marking.
  6. Manual attendance: Tick-box list to mark present students when the camera is not available. Shows who is already present today.
  7. Reports & export: Attendance records filtered by subject, date range and student, per-student attendance percentage, and CSV export.

Requirements

  • Python 3.10 or newer
  • A laptop webcam or USB webcam (manual attendance works without one)
  • Internet connection for the one-time pip install (about 2-4 minutes)
  • Windows, macOS or Linux (Tkinter is included with Python)

How to run this project

  1. Install Python 3.11 from python.org and tick "Add python.exe to PATH" during setup.
  2. Extract the zip and open the project folder (STUDENT_GUIDE.md explains every step in simple words).
  3. Double-click `1_INSTALL.bat` once and wait until it says [OK] (about 2-4 minutes; it downloads the libraries into a private .venv folder).
  4. Double-click `2_RUN.bat` to start the project. If it does not start, double-click `CHECK_SETUP.bat` and read what it says.
  5. Log in with **admin / admin123**. In the Students tab, add a student and click Capture Face, then click Train Model.
  6. In Take Attendance, choose a subject and click Start Face Attendance (press Q to stop). Then open Reports to show the attendance % and export the CSV in your review.

More AI / ML projects