A Survey of Face Recognition Methods based on Deep Learning

Abstract

Since the 21st century, people have put forward higher requirements for information security technology in many fields such as society and economy. The requirement has promoted the development of biometric identification technology. Face recognition technology has become a research hotspot in biometric identification technology with its unique advantages. In recent years, with the development of deep learning, face recognition technology has made breakthroughs. Face recognition technology based on deep learning has been widely used in various fields such as finance, education, security, transportation, and new retail. In the process of face recognition technology becoming popular, some comprehensive literatures are urgently needed to summarize the methods of face recognition technology. Based on this, this paper first introduces the principle and existing problems of traditional face recognition methods, and then introduces in detail two typical face recognition methods based on deep learning—face recognition methods based on convolutional neural networks and face recognition methods based on deep belief networks. Finally, we provide an overview of common face datasets.