Research on Face Recognition Based on Cubic Spline Weight Function Neural Network
This paper investigates face recognition technology,compares and analyzes the differences between traditional recognition technology and recognition technology based on Deep Learning.It is pointed out that due to the complex network structure of Deep Learning,the phenomenon of algorithm overfitting is prone to occur in the face recognition process.In response to the overfitting problem mentioned above,this paper studies the face recognition algorithm based on weight function neural network.This type of neural network has a simple structure with only two layers of input and output,and takes face images as input information.The training objective of the network is to calculate the cubic spline weight function.The simulation experiments show that this type of network has good recognition accuracy and efficiency.
face recognitioncubic spline weight functionneural network
国家科技期刊平台
NSTL
万方数据
