(Retracted) Face recognition technology in classroom environment based on ResNet neural network

Abstract

With the rapid development of electronic computers and information technology, face recognition is widely used in fields such as enterprises, entertainment, information security, and daily life. However, the current face recognition technology is still relatively poor in distinguishing facial features, resulting in a low accuracy of face recognition, which cannot meet increasing application requirements. For this reason, it is necessary to develop more accurate face recognition technology. Residual neural network (ResNet) neural network is a deep residual learning convolutional neural network, which can be used to solve the degeneration problem (i.e., after adding more layers to the neural network, the performance drops rapidly) of deep-learning neural networks. We aim to study the specific principles, calculation methods, and characteristics of the ResNet neural network, analyze the complexity of the classroom environment, propose the use of ResNet network for face feature extraction, and use additive angular margin loss for deep face recognition (ArcFace) as the loss function of the ResNet network to improve the ResNet network. Because the ArcFace function has the advantages of high performance, easy programming, low complexity and high training efficiency. We use this scheme to conduct field tests of face recognition on many students in the classroom. The test results show that this scheme enhances the discrimination of facial features and improves the accuracy of face recognition. In the case of different numbers of people, facial defects, and strong light exposure, the system can still detect and recognize faces stably. In the case of facial defects, the recognition accuracy rate is still 63.3%, and the recognition accuracy rate is still more than 60% under the illumination of strong light, and the recognition accuracy rate under correct conditions is more than 70%.

Hybrid YOLOv3 and ReID intelligent identification statistical model for people flow in public places

“…The ArcFace loss function was combined to optimize the ResNet network to achieve the face detection accuracy. Experimental results showed that the model stably detected and recognized faces even under facial defects and bright light exposure 14 .…”

Real-time emotion recognition using end-to-end attention-based fusion network

“…30,31 Moreover, emotions are not always clearly detected when the faces are sweating. However, CNN has improved recognition accuracy due to the growing calculating power, and many networks have been proposed, such as U-Net, 19 ResNet, 20 and VGG net. 16,32 The proposed method has three modules, as shown in Fig.…”

“…The significant improvement in deep learning and the implementation of CNN has been quite promising 19 – 21 A major problem with deep learning is that a huge amount of data is required to train successful models. The CNN algorithm has made some improvements in the detection of facial expressions, but there are still some detachments in place, including too long training times and low recognizing rates in the complex environment.…”

“…The U-Net 19 helps autoencoder-based segmentation models overcome their inherent drawbacks (downsampling operations lead to loss of edge details). Residual-style Net (ResNet) 20 can also be used as a baseline, but ResNet 20 takes weeks to be trained. Thus its accuracy is still lower for real-world sweating-based face detection applications.…”