AI-Powered Smart Examination Integrity System using Embedded Camera Processing, Mobile Integration, and a Web-Based Monitoring Platform for Automated Malpractice Detection in Educational Institutions.
Live Monitoring Dashboard with Real-time Detection
AI-Powered Violation Detection & Alert System
Camera Connection & System Configuration
Integrity Scoring & Evidence Management
Comprehensive Reports & Analytics
- YOLOv8 Object Detection - Detects phones, chits, textbooks, notebooks, electronic devices
- MediaPipe Head Pose Estimation - Analyzes head movements and gaze direction
- ByteTrack Person Tracking - Persistent multi-person tracking with unique IDs
- 3-Phase Detection System:
- Head Count - Automatic student counting and attendance verification
- Behavior Analysis - Suspicious posture and movement detection
- Prohibited Item Detection - Real-time detection of cheating materials
- Mobile Camera Connection - Use any smartphone as a wireless IP camera
- Video Upload - Process pre-recorded examination footage
- Direct Webcam - Built-in laptop camera support
- Claymorphism Design - Soft, modern 3D-like interface
- Fully Responsive - Works seamlessly on laptop and mobile devices
- Real-time Alerts - Instant notifications for invigilators
- Evidence Capture - Automatic screenshot and video clip extraction
┌─────────────────────────────────────────────────────────┐
│ VIDEO INPUT SOURCES │
│ ┌────────────────────┐ ┌────────────────────┐ │
│ │ Mobile Camera │ │ Video Upload │ │
│ │ (IP Webcam App) │ │ (MP4/AVI/MOV) │ │
│ └──────────┬─────────┘ └──────────┬─────────┘ │
└─────────────┼──────────────────────────┼────────────────┘
│ │
▼ ▼
┌─────────────────────────────────────────────────────────┐
│ EMBEDDED AI PROCESSING ENGINE │
│ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ │
│ │ Phase 1: │ │ Phase 2: │ │ Phase 3: │ │
│ │ Head Count │→ │ Behavior │→ │ Prohibited │ │
│ │ (YOLOv8) │ │ Analysis │ │ Items │ │
│ │ │ │ (MediaPipe) │ │ (YOLOv8) │ │
│ └──────────────┘ └──────────────┘ └──────────────┘ │
│ │ │
│ ▼ │
│ ┌────────────────────┐ │
│ │ Scoring Engine │ │
│ │ & Alert System │ │
│ └────────────────────┘ │
└─────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────┐
│ WEB APPLICATION (React + FastAPI) │
│ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ │
│ │ Live Monitor │ │ Upload │ │ Reports │ │
│ │ Dashboard │ │ & Analyze │ │ History │ │
│ └──────────────┘ └──────────────┘ └──────────────┘ │
└─────────────────────────────────────────────────────────┘
- Node.js 18+ and npm
- Python 3.11+
- Git
# Clone the repository
git clone https://github.com/Rohithdgrr/Embedded-system-project.git
cd Embedded-system-project
# Install frontend dependencies
npm install
# Install AI backend dependencies
cd ai_backend
pip install -r requirements.txt
cd ..
# Install backend dependencies
cd backend
pip install -r requirements.txt
cd ..# Start all services (Windows)
start-all.bat
# Or start individually:
npm run dev # Frontend (Vite)
cd ai_backend && python src/detector.py # AI Backend
cd backend && python app.py # API Backend| Technology | Purpose |
|---|---|
| React 18 | UI Framework |
| TypeScript | Type Safety |
| Tailwind CSS | Styling |
| Framer Motion | Animations |
| Lucide React | Icons |
| Vite | Build Tool |
| Technology | Purpose |
|---|---|
| YOLOv8 | Object Detection |
| MediaPipe | Pose Estimation |
| OpenCV | Video Processing |
| NumPy | Numerical Computing |
| Flask | API Server |
| Technology | Purpose |
|---|---|
| Vercel | Frontend Hosting |
| Render | AI Backend Hosting |
| SQLite | Database |
| Violation Type | Points | Severity |
|---|---|---|
| Phone Detected | 30 | 🔴 High |
| Chit/Slip Detected | 25 | 🔴 High |
| Textbook Detected | 30 | 🔴 High |
| Notebook Detected | 25 | 🟠 Medium |
| Electronic Device | 20 | 🟠 Medium |
| Head Turn (Sustained) | 10 | 🟡 Low |
| Looking at Neighbor | 8 | 🟡 Low |
| Leaning Toward Other | 10 | 🟠 Medium |
| Passing Gesture | 15 | 🟠 Medium |
| Head Count Mismatch | 40 | 🔴 High |
| Extra Person in Hall | 50 | 🔴 Critical |
- 🌐 Live Website: https://embedded-system-project.vercel.app/
- 👨💻 Portfolio: https://rohithdgrr.github.io/Protfolio/
- 📁 Repository: https://github.com/Rohithdgrr/Embedded-system-project
This project is licensed under the MIT License - see the LICENSE file for details.
Made with ❤️ using React, TypeScript, Python, and YOLOv8
© 2026 ExamShield AI. All rights reserved.