Research on face recognition technology based on an improved LeNet-5 system
Ruian Liu, Yilin Liu, Zhenhai Wang, Hongyu Tian · 2022
With the continuous development of technology, face recognition technology became highly valued in the current society. In this paper, a deep convolutional neural network structure with deconvolution is constructed with the Keras framework based on the theory of deep learning. The LeNet-5 network structure is improved by adding the deconvolution layer. Meanwhile, a face recognition system is also designed. The performed experiment demonstrates that this method exhibits high accuracy and can accurately identify faces presented in videos.