Machine Learning-Based Face Recognition Attendance System Using LBPH Algorithm

In educational institutions, maintaining accurate and efficient attendance records is crucial for monitoring student participation and engagement. Traditional attendance marking methods, such as roll calls and manual sign-ins, are time-consuming, prone to errors, and susceptible to fraudulent practices like proxy attendance. To address these limitations, this research presents a Machine Learning-Based Face Recognition Attendance System Using the Local Binary Patterns Histogram (LBPH) Algorithm. The proposed system leverages computer vision and machine learning techniques to automate the attendance marking process, ensuring accuracy, efficiency, and security. The system consists of two primary modules: face detection and face recognition. The OpenCV-based LBPH algorithm is employed for facial feature extraction and matching, as it is robust against variations in lighting conditions, facial expressions, and slight head movements. The system captures real-time facial images, processes them through feature extraction, and compares them with a pre-registered database to identify students and record their attendance. The attendance records are then stored in a structured database for easy access and analysis. Compared to traditional methods and other biometric techniques such as RFID-based and fingerprint-based attendance systems, the proposed face recognition approach offers a contactless, non-intrusive, and efficient solution that enhances both security and usability. Experimental results demonstrate that the system achieves high accuracy and real-time processing capabilities, making it a practical solution for educational institutions. Future enhancements may include integrating deep learning models for improved recognition accuracy, cloud-based storage for remote access, and multi-modal biometric authentication for added security.