A Lightweight Face Recognition Model Using Convolutional Neural Network for Monitoring Students in E-Learning

Abstract

Using convolution neural network (CNN) for face recognition is being widely research with a promising significant in applications and it is interested by many authors. Moreover, the CNN model has brought successful applications in practice such as detection and identification face of people on Facebook users' photos application, they use DeepFace model. There are many articles which proposed CNN models for face recognition with using some modifications of popular models of large architectures such as VGG, ResNet, OpenFace or FaceNet. However, these models are large complexity for some applications in reality with limitations of computing resources. This paper proposes a design of CNN model with moderate complexity but still ensures the quality and efficiency of face recognition. We run experiments for evaluating the model on some popular datasets, the experiment shows effective results and indicates that the proposed model can be practically used.