PopularMajor Project
Artificial Intelligence
Face Recognition Attendance System
Camera-based attendance with liveness detection and analytics
- Python
- OpenCV
- FaceNet
- Flask
- +2
₹4,900₹5,999
4.8/301 reviews
Artificial Intelligence · Major Project
Driver Drowsiness Detection with Emergency Alert
Eye closure and yawns trigger an alarm and an SMS to a contact
2-3 weeks build
Overview
A dash-mounted webcam tracks facial landmarks and computes eye aspect ratio and mouth aspect ratio every frame. Sustained eye closure or repeated yawning sounds a local alarm, and if the driver does not respond, the system sends an SMS with a timestamp to a saved emergency contact through the Twilio API. Thresholds calibrate to each driver at start-up.
What makes it stand up
- 01Eye and mouth aspect ratios from MediaPipe face landmarks
- 02Per-driver calibration instead of one fixed threshold
- 03Escalation from audible alarm to emergency SMS
- 04Head-pose check for nodding off with eyes half open
- 05Trip log of every drowsy event with a timeline chart
Module breakdown
- 01
Landmarks
Face mesh tracking and eye and mouth point extraction.
- 02
Metrics
EAR, MAR and head-pitch computed per frame.
- 03
Decision logic
Time windows and calibration to reduce false alarms.
- 04
Alerts
Local alarm plus Twilio SMS to the saved contact.
- 05
Trip dashboard
Flask page with event log and fatigue timeline.
After this, you will be able to
- Explain the eye aspect ratio formula and why it works
- Defend your time windows against false alarms
- Demo the alarm and SMS firing live
Technology stack
- Python
- OpenCV
- MediaPipe
- Flask
- Twilio
- Level
- Major Project
- Domain
- Artificial Intelligence
- Build time
- 2-3 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support