Information Model For Verifying The Authenticity Of Distance Education Users' Faces Through Video Images

Abstract

The expansion of distance education systems, especially during the COVID-19 pandemic, has played a crucial role in ensuring uninterrupted learning at educational institutions. However, ensuring the security of these systems and monitoring academic integrity remain pressing issues. Traditional authentication methods (such as login and password) are not sufficiently reliable for authenticating the identity of users. Consequently, the need for biometric authentication, particularly facial recognition technologies, is increasing. This study presents an advanced information model for verifying the authenticity of a user’s face in distance education through video footage. The model is based on convolutional neural networks (CNN) and employs robust tools such as dlib for facial detection and verification algorithms. The collected video data is analyzed under various conditions (lighting, angle changes, and facial expressions), ensuring the model’s stability and accuracy. The scientific foundation of the model lies in the deep learning methods, which are highly effective for in-depth analysis of images and extracting biometric facial features. The process of assessing facial authenticity incorporates algorithms that consider the 3D structure of the face, thereby providing protection against spoofing attacks (such as using photos or videos for forgery). The model’s efficiency was demonstrated in comprehensive testing, achieving a facial authenticity detection accuracy of 95%. The proposed information model has significant practical importance for making distance education systems more secure and reliable. In the future, integrating this approach with other biometric authentication methods could further enhance the security of distance learning environments