A novel Face Recognition System based on Jetson Nano developer kit

Abstract

Real-time face recognition became more important in the last two decade, it is adopted universally for attacking crime, stopping fraud, ensuring public safety. It proves that it is one of the most reliable biometrics security systems because frames can be taken from cameras without touching or interacting, and those images recorded and spontaneously validated with existing databases. The methodology achieved in this work will deal with several challenges like real-time recognition, cheap, portable, and reliable system. NVIDIA Jetson Nano is used in this work. It is a tiny, powerful AI computer that delivers the estimated performance to run advanced AI workloads with a small size, low-power, and low-cost. The main goal of this research is to deploy a deep learning model for face recognition in Jetson Nano, with the intention of real-time performance and high accuracy. The results of this study have shown great real-time performance in face recognition using Jetson Nano, Where it was processing 8.9 FPS in comparison with the latest raspberry pi edition 2.6 FPS.