Skip to content

Developed an AI-powered proctoring system utilizing Python, Mediapipe, and advanced landmarking techniques to ensure integrity in online exams.

Notifications You must be signed in to change notification settings

muradaghyv/Proctoring-Project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

Proctoring-Project

Description: In the wake of increasing demand for remote learning and online examinations, ensuring exam integrity has become a critical challenge. Our AI-Driven Online Exam Proctoring System addresses this challenge by leveraging cutting-edge computer vision techniques to monitor and analyze student behavior during online exams. This project integrates multiple advanced technologies to provide a robust, reliable, and scalable solution for academic institutions and certification bodies.

Key Technologies and Techniques:

Python: Utilized for its powerful libraries and frameworks, facilitating seamless integration and efficient processing. Mediapipe: Deployed for its state-of-the-art real-time face detection and facial landmark tracking capabilities, enabling precise monitoring of head and eye movements. Landmarking Techniques: Implemented to ensure accurate detection and analysis of facial features, crucial for identifying suspicious behaviors. Matplotlib: Employed for its comprehensive plotting functionalities, allowing for clear visualization of data and results. Key Features:

Suspicious Behavior Detection: The system automatically identifies and timestamps suspicious activities, such as frequent head movements, looking away from the screen, or potential attempts to consult unauthorized resources. Head and Eye Position Tracking: Detailed tracking of head and eye positions throughout the exam session, providing valuable insights into the examinee's focus and behavior. Dataframe Output: Generates a comprehensive dataframe containing timestamps, head position, and eye position values, facilitating in-depth analysis and reporting. Result Visualization: Utilizes Matplotlib to create clear and informative plots, enabling easy interpretation of the tracked data and detected anomalies. Scalability: Designed to handle large volumes of exam recordings, making it suitable for use in diverse educational settings. Impact: This project significantly enhances the reliability and fairness of online examinations. By automating the proctoring process, it reduces the burden on human proctors, minimizes the risk of human error, and ensures consistent monitoring standards. The detailed analysis and visualizations provided by the system offer valuable insights for educators and administrators, aiding in the identification of integrity issues and the improvement of examination processes.

Future Directions: We aim to further enhance the system's capabilities by integrating additional machine learning algorithms to improve detection accuracy, expanding its functionality to monitor other suspicious activities, and optimizing its performance for real-time applications.

About

Developed an AI-powered proctoring system utilizing Python, Mediapipe, and advanced landmarking techniques to ensure integrity in online exams.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •  

Languages