Abstract
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.
Subject
General Physics and Astronomy
Reference10 articles.
1. Fuzzy Support Vector Machines for Face Recognition: A Review [J];Prakash;Maropoulos P G.,2015
2. Learning Compact Binary Face Descriptor for Face Recognition [J];Lu;IEEE Transactions on Pattern Analysis and Machine Intelligence,2015
3. Kernel sparse representation-based classifier ensemble for face recognition [J];Zhang;Multimedia Tools and Applications,2015
4. Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition [J];Ding;IEEE Transactions on Pattern Analysis & Machine Intelligence,2016
5. Face recognition based on the proximity measure clustering [J];Nemirovskiy;Institute of Cybernetics of Tomsk Polytechnic University,2016
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献