Mask-Robust Face Verification for Online Learning via YOLOv5 and Residual Networks

2025-10-29

AI Summary

To address the degradation of facial recognition robustness caused by face masks during pandemic-induced online education, this paper proposes a lightweight identity authentication method integrating YOLOv5 with an enhanced residual network. First, YOLOv5 is employed for high-accuracy, low-latency face detection. Second, a channel-attention-enhanced residual feature extraction network is designed to strengthen discriminative feature representation under mask occlusion. Finally, end-to-end face verification is performed via Euclidean distance metric. The method is trained and evaluated on a self-collected masked-face dataset, achieving a verification accuracy of 98.2% under challenging conditions—including complex illumination, large pose variations, and partial occlusions—significantly outperforming baseline models. This work delivers a secure, stable, and practical identity authentication solution tailored for online teaching environments.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Adversarial Learning & Robustness
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Security and Privacy: Authentication, authorization, and access control

Abstract

In the contemporary landscape, the fusion of information technology and the rapid advancement of artificial intelligence have ushered school education into a transformative phase characterized by digitization and heightened intelligence. Concurrently, the global paradigm shift caused by the Covid-19 pandemic has catalyzed the evolution of e-learning, accentuating its significance. Amidst these developments, one pivotal facet of the online education paradigm that warrants attention is the authentication of identities within the digital learning sphere. Within this context, our study delves into a solution for online learning authentication, utilizing an enhanced convolutional neural network architecture, specifically the residual network model. By harnessing the power of deep learning, this technological approach aims to galvanize the ongoing progress of online education, while concurrently bolstering its security and stability. Such fortification is imperative in enabling online education to seamlessly align with the swift evolution of the educational landscape. This paper's focal proposition involves the deployment of the YOLOv5 network, meticulously trained on our proprietary dataset. This network is tasked with identifying individuals' faces culled from images captured by students' open online cameras. The resultant facial information is then channeled into the residual network to extract intricate features at a deeper level. Subsequently, a comparative analysis of Euclidean distances against students' face databases is performed, effectively ascertaining the identity of each student.

Problem

• Face verification for online learning authentication
• Mask-robust identity recognition using YOLOv5
• Feature extraction via residual networks for security

Innovation

• YOLOv5 network detects faces from camera images
• Residual network extracts deep facial features
• Euclidean distance compares features with student database