A Comprehensive Review on Face Recognition, Anti-Spoofing Liveness Verification and Automated Dress Code Enforcement Techniques for Smart Attendance Framework

Abstract

Smart attendance systems have emerged as an effective alternative to traditional attendance management approaches by leveraging advancements in artificial intelligence, computer vision, and deep learning. Face recognition technology enables contactless and automated identification of individuals, reducing manual effort and minimizing proxy attendance. However, the increasing deployment of facial recognition systems has exposed vulnerabilities to presentation attacks such as printed photographs, replay videos, and three-dimensional masks. To address these challenges, anti-spoofing liveness verification techniques have been integrated into attendance systems to ensure that only genuine users are authenticated. Simultaneously, educational institutions and organizations increasingly seek automated dress code monitoring solutions to enforce uniform policies and maintain discipline. Recent developments in object detection and image classification models have enabled real-time dress code compliance verification using surveillance cameras. This review paper presents a comprehensive analysis of face recognition, anti-spoofing liveness verification, and automated dress code enforcement techniques published between 2020 and 2026. The study examines major algorithms, datasets, performance metrics, implementation challenges, and deployment considerations. Furthermore, research gaps are identified, and a unified smart attendance framework is proposed that integrates identity verification, liveness detection, and dress code compliance monitoring into a secure and scalable solution. Existing literature indicates that while significant progress has been achieved in individual domains, fully integrated systems remain limited, creating opportunities for future research and development.