Skip to content

An AI-powered proctoring system utilizing YOLOv5, MediaPipe, and OpenCV for real-time detection of phones, multiple faces, eye tracking, and suspicious activity during online assessments. Features audio alerts, logging, and automated violation tracking.

Notifications You must be signed in to change notification settings

Kevalshah91/Advanced-Proctoring-System

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

📌 Advanced Proctoring System

Python
OpenCV
YOLOv5

🚀 Overview

The Advanced Proctoring System is an AI-powered tool designed to monitor online exams by detecting:
Phones & electronic devices using YOLOv5
Face absence & multiple faces to prevent impersonation
Eye tracking & looking away detection using MediaPipe
Real-time alerts, logging, and violation tracking

🛠️ Features

✔️ Real-time monitoring with OpenCV
✔️ YOLOv5-based phone detection (optimized for multiple classes)
✔️ Face & eye detection with Haar cascades
✔️ Live audio alerts for violations
✔️ Automated logging & violation reports
✔️ Cross-platform compatibility (Windows, Linux, macOS)

🔄 System Flowchart

graph TD;
    A[Start] --> B[Initialize Systems]
    B -->|Load YOLOv5| C[Phone Detection]
    B -->|Load MediaPipe| D[Face & Eye Tracking]
    B -->|Initialize Logging| E[Logging & Reports]

    C -->|Detect Phones| F[Violation Check]
    D -->|Detect Multiple Faces| F
    D -->|Track Eye Movement| F

    F -->|No Violations| G[Continue Monitoring]
    F -->|Violation Detected| H[Trigger Alert & Log]
    H --> I[Capture Screenshot & Record]

    I --> J[Store in proctoring_logs/]
    J --> K[Generate Report]

    G --> B
    H --> B
    K --> L[End]
Loading

📜 Logging & Reports

📝 Violation logs are stored in the proctoring_logs/ folder.

📌 Future Improvements

  • 🔍 Enhance accuracy with deep learning-based face tracking
  • 🎙️ Voice detection for verbal cheating detection
  • 📊 Web-based dashboard for real-time analytics

About

An AI-powered proctoring system utilizing YOLOv5, MediaPipe, and OpenCV for real-time detection of phones, multiple faces, eye tracking, and suspicious activity during online assessments. Features audio alerts, logging, and automated violation tracking.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages