Application Research of Computer Virtual Reality Technology in Big Data Information Face Recognition System

This paper studies the edge-cloud collaborative face recognition technology. This project intends to integrate cloud computing technology with boundary computing technology, breaking through the limitations of traditional algorithms on network environment and expanding the scope of application of algorithms. This improves the efficiency of the user. The image feature extraction algorithm based on Resent is studied, and the ResNet34 network is perfected. By introducing the face loss function of ArcFace to guide the training of the network, the network can better understand the corner features of the face. In the boundary aspect, this project intends to study the lightweight Resent structural model based on depth-separable volume to solve the problem of limited computation and memory. The SResNet model based on the lightweight Resent structure is studied. The effectiveness and real-time performance of this method are verified by the facial recognition experiments on edge cloud collaboration.