Face Fusion Register

Attendance management is a critical aspect of academic institutions, ensuring student participation and discipline. Traditional methods, such as manual roll calls, are time-consuming and prone to errors, including proxy attendance. To address these challenges, this paper presents the Face Fusion Register, an automated attendance system that utilizes Haar Cascade classifiers for real-time face detection. The system captures student images, detects faces, and marks attendance by matching them against a pre-stored database. A key feature is its automated message notification, which informs students once their attendance is recorded. This enhances transparency and eliminates the need for manual verification. Unlike deep learning-based models, the Haar Cascade approach ensures a lightweight, fast, and efficient solution suitable for real-time classroom environments. Experimental results demonstrate the system’s accuracy, speed, and reliability in detecting faces and notifying students instantly. While effective under normal conditions, improvements in handling variations like side profiles and occlusions remain an area for future work. Overall, the Face Fusion Register provides an efficient, scalable, and automated alternative to traditional attendance systems.