Welcome to the Guard AI project !! 🚨
Guard AI is a lightweight, AI-powered exam monitoring tool that provides real-time proctoring by detecting suspicious activities during online exams such as unauthorized speaking, gaze deviation, and usage of restricted websites.
Lip Movement Detection + Audio Analysis Detects if the user is speaking during the exam. Differentiates between yawning and speaking.
Tracks user's eye and head movement. Detects if the user looks away from the screen.
Detects if the user opens any non-permitted websites. A warning signal is provided if done so.
Summarizes user behavior during the exam. Includes start and end times of suspicious activities. Generates a clean PDF report after each test session.
guard_ai_project/ │ ├── features/ │ ├── init.py │ ├── lip_detection.py │ ├── gaze_tracking.py │ └── website_monitor.py │ ├── logs/ │ ├── lip_audio_logs.txt │ ├── gaze_tracking_logs.txt │ └── website_usage_logs.txt │ ├── reports/ │ └── final_report.pdf (auto-generated) │ ├── main.py ├── generate_report.py ├── README.md ├── requirements.txt
🔧 **Installation** :- 1. Clone the repository: git clone https://github.com/your-username/guard-ai-project.git 2. Install the required libraries: pip install -r requirements.txt
1. Run the application: python main.py
-
After finishing, you can generate an intermediate report.
-
At the end, generate a final comprehensive PDF report.
Reports will be generated automatically in the reports/ folder.
The report includes: Activities detected. Time intervals. Observations.
Developed by Nikhil Balamurugan and Vishaal Pillay👨💻
This project is licensed under the MIT License.