Abstract: The Facial Recognition System for Access Control through the Application of Convolutional Neural Networks, is a novel approach to enhance security in organizations by accurately identifying individuals before granting them access to restricted areas. The system employs a pre-trained convolutional neural network (CNN) architecture and fine-tunes it with a dataset of facial images for training. The images undergo pre-processing to remove noise, normalize illumination, and align faces to improve recognition accuracy. The proposed system's performance is evaluated based on accuracy rates, with an overall accuracy of 96.67% and an F1- score of 0.97, surpassing traditional face recognition methods. The system's versatility allows its application in various contexts, including security systems for public transportation, border control, and financial institutions. This research highlights the potential of CNNs for facial recognition systems and emphasizes the importance of utilizing advanced techniques for access control in organizations.

Keywords: Convolutional Neural Network, Transfer Learning, Face Recognition, Artificial Intelligence.

PDF | DOI: 10.17148/IJARCCE.2023.12558

Open chat
Chat with IJARCCE