Artificial Intelligence
Face Recognition Attendance System
Camera-based attendance with liveness detection and analytics
- Python
- OpenCV
- FaceNet
- Flask
- +2
Artificial Intelligence · Capstone
Flags helmetless and triple riding, signal jumps and drafts a challan
Overview
Junction CCTV footage runs through a YOLOv8 detector for riders, helmets and vehicles, while a virtual stop line tied to the signal state catches red-light jumps. Offending plates are cropped and read with OCR, and each violation lands in an officer dashboard as a draft challan with evidence frames, awaiting human approval before it is issued.
What makes it stand up
Module breakdown
YOLOv8 fine-tuned on riders, helmets, vehicles and plates.
Zone, line and signal logic that turns detections into offences.
Crop, deskew and OCR with format validation.
FastAPI backend that drafts challans and stores evidence.
React review queue with approve, reject and export actions.
After this, you will be able to
Technology stack
You receive
Keep looking
Artificial Intelligence
Camera-based attendance with liveness detection and analytics