Data Science in Face Recognition System Based on BP Neural Network
Ziqiang Ma, Guidong Zhang · Journal of Physics Conference Series · 2021
Abstract With the rapid development of economy, people have higher and higher requirements for the performance of security system. The traditional access control system based on face recognition based on deep learning has gradually replaced the traditional access control system. This paper mainly describes the concepts of BP neural network and face recognition, and improves and designs a face recognition system. The detection accuracy of the system reaches 97.8%, the false detection rate is 0.8%, and the leakage rate is 0.8% the detection rate is 1.4%, and the accuracy of face recognition is 96.7%, which can well meet the requirements of contemporary face recognition.