<![CDATA[In this paper, we present a robust facial recognition system designed to identify students at Department of Informatics in Universitas Malikussaleh using a Convolutional Neural Network (CNN) algorithm, specifically the VGG16 architecture. The advancement of information technology and machine learning has significantly improved facial recognition capabilities, establishing it as a reliable alternative to traditional identification methods such as fingerprinting and iris scanning. Our approach leverages a diverse dataset captured from five different angles, enhancing the representation of facial features and improving model training. The system development comprises several critical stages, including image acquisition, preprocessing, model training with training and validation data, and performance evaluation. Experimental results indicate that the CNN model achieves an impressive accuracy of 99.09% on training data and 100% on both validation and testing datasets. These findings affirm the model's high classification accuracy across the tested classes, underscoring the effectiveness of the VGG16-based CNN in facial recognition applications. The implications of this study suggest that the developed system can significantly enhance digital attendance and security systems, catering to the growing demand for reliable AI-driven security technologies in contemporary society. We anticipate that with its promising outcomes, this system can be implemented on a larger scale, contributing to the ongoing advancement of AI-based security solutions.]]>
