Attendance Management System Using Face Recognition

Abstract

The increasing demand for accurate and efficient attendance monitoring in educational and organizational settings has led to the adoption of biometric-based solutions. Conventional methods such as manual registers, RFID cards, and fingerprint scanners are time-consuming, error-prone, and susceptible to proxy attendance. Recent research (2021–2025) highlights face recognition as an emerging technology that enables a contactless, reliable, and real-time solution for attendance automation.

This paper presents a Face Recognition-Based Attendance Management System developed using Python and OpenCV’s Local Binary Patterns Histogram (LBPH) algorithm. The system captures real- time video through a webcam, detects and recognizes faces against a pre-trained dataset, and automatically records attendance into CSV files with the corresponding timestamps. Compared to traditional biometric systems, LBPH is computationally efficient, robust to lighting variations, and performs effectively with small datasets, making it suitable for classrooms and workplace environments.
Further literature from 2021–2025 indicates the
growing integration of deep learning methods such as Convolutional Neural Networks (CNNs) and FaceNet models for enhanced accuracy and


scalability. While this work utilizes the LBPH algorithm for simplicity and cost-effectiveness, its architecture provides a foundation for future integration of deep learning models to achieve improved recognition rates in large-scale environments.