Intelligent Proctoring System Using OpenCV, Mediapipe, Dlib & Speech Recognition

ProctorAI: Intelligent Proctoring System Using OpenCV, Mediapipe, Dlib & Speech Recognition

ProctorAI is a real-time AI-based proctoring solution that uses computer vision and audio analysis to detect suspicious activities during exams or assessments.

👉 View GitHub Repository

🔍 Key Features

• Face detection and tracking using Mediapipe and Dlib
• Eye and pupil movement monitoring for head and gaze tracking
• Audio detection for identifying background conversation
• Multi-screen detection via active window tracking
• Real-time alert overlays on camera feed
• Interactive quit button on the camera feed

⚙️ How It Works

1. Webcam feed is captured using OpenCV
2. Face and eye landmarks detected using Mediapipe
3. Dlib tracks pupil movement from eye regions
4. System checks head movement, gaze, and face presence
5. Running applications scanned using PyGetWindow
6. Background audio analyzed using SpeechRecognition
7. Alerts displayed in real time on suspicious activity

🧠 Tech Stack

• OpenCV – Video capture and rendering
• Mediapipe – Face and landmark detection
• Dlib – Pupil detection and geometry
• SpeechRecognition – Audio analysis
• PyGetWindow – Application window tracking
• Threading – Parallel detection modules

🚨 Alerts Triggered By

• Missing face (student leaves or covers webcam)
• Sudden or excessive head movement
• Unusual pupil movement
• Multiple open windows
• Background voice detection

📦 Installation

git clone https://github.com/anirbanduttaRM/ProctorAI
cd ProctorAI
pip install -r requirements.txt

Download shape_predictor_68_face_landmarks.dat from dlib.net and place it in the root directory.

▶️ Running the App

python main.py

🖼️ Screenshots

🎥 Demo Video

📌 Future Improvements

• Face recognition for identity verification
• Web-based remote monitoring
• Data logging and analytics
• Improved NLP for audio context

🤝 Contributing

Pull requests are welcome. For major changes, open an issue first.

📄 License

Licensed under the MIT License — see the LICENSE file.

---

Made with ❤️ by Anirban Dutta