Technical Name Real time face detection and recognition for access control system application
Project Operator National Central University
Project Host 蔡宗漢
Summary
This technology construct a face detection and recognition system with deep neural network to implement an access control system. This technique can replace the keys or ID card to achieve a human centric computing system.
Scientific Breakthrough
The face detection block can reach 85% precision rate on WIDERFACE dataset, and can reduce the error detection with catching the feedback generated by face recognition block. The face recognition block can achieve 99% precision on VGGFace2 dataset
Industrial Applicability
This technology can assists our lives through monitors and related algorithms, improving the convenience, security of the environment.
Keyword deep learning convolution neural network face detection face recognition access control system neural network image processing computer vision deep neural network face tracking
other people also saw