Sample project · CSE
Smart attendance with face recognition
Students check in by looking at the camera; the system recognises them and logs attendance.
Try it live
A sample our team built to show the standard of a delivered project, not client work. The demo runs face detection and recognition in your browser with face-api.js. Nothing leaves your device: your camera feed and face data stay in this tab and are cleared when you close it.
Runs on your device. Your camera feed and face data never leave this tab.
Today's attendance
2 checked in
- Ananya (sample)09:0271%
- Rohan (sample)09:0466%
Each person is checked in once per session. Match is how close your face is to the enrolled one (100% is identical).
What it solves
Roll calls waste lecture time and proxy attendance is easy. The project replaces them with a webcam check-in that recognises each enrolled student and keeps a timestamped log.
Features
- Enrol a student from a few webcam frames
- Real-time face detection and recognition
- One check-in per student per session
- Attendance log with timestamps and CSV export
- Admin dashboard: daily and monthly attendance
How it works
- Webcam frame
- Face detection
- 128-d face embedding
- Match against enrolled students
- Attendance record in the database
- Dashboard and CSV export
Tech stack
- Python
- Flask
- OpenCV
- face_recognition
- SQLite
- Chart.js
Machine learning & web · CSE
Report, slides and viva prep
Every project ships with a full report, a presentation deck and viva preparation. Here is a look at this one.
Contents
Smart attendance with face recognition
- Abstract
- 1. Introduction
- 2. Literature survey
- 3. System requirements
- 4. System design (architecture, DFD, ER)
- 5. Implementation
- 6. Testing and results
- 7. Conclusion and future scope
- References
Smart attendance with face recognition
How recognition works
- Detect the face in each frame
- Turn it into a 128-number embedding
- Match it to the nearest enrolled student
Final year project review · Project Squad sample
Viva questions we prepare you for
- Why use face embeddings instead of comparing images directly?
- How do you set the matching threshold, and what happens if it is too loose?
- How would you stop someone checking in with a photo?
Ready to stop stressing? Start with a free call.
Free 30-minute consult, no commitment. We’ll tell you honestly whether your topic will pass review and what it’ll take to deliver.