Abstract
Biometric recognition technologies have become more important in the modern society due to their convenience with the recent informatization and the dissemination of network services. Among such technologies, face recognition is one of the most convenient and practical because it enables authentication from a distance without requiring any authentication operations manually. As far as we know, face recognition is susceptible to the changes in the appearance of faces due to aging, the surrounding lighting, and posture. There were a number of technical challenges that need to be resolved. Recently, remarkable progress has been made thanks to the advent of deep learning methods. In this position paper, we provide an overview of face recognition technology and introduce its related applications, including face presentation attack detection, gaze estimation, person re-identification and image data mining. We also discuss the research challenges that still need to be addressed and resolved.
Highlights
Unlike using passwords or physical keys, biometrics technology has great potential to usher in a new world where nobody needs to be conscious of authentication or identification processes
In 2004, our face recognition technology was incorporated into an immigration administration system, which has since been deployed in 45 countries
We developed a novel hierarchical scheme combined with face and eye detection in 2005 [5] by using generalized learning vector quantization (GLVQ) [6] as a classifier to improve performance
Summary
Unlike using passwords or physical keys, biometrics technology has great potential to usher in a new world where nobody needs to be conscious of authentication or identification processes. Face recognition technology is evolving very rapidly in terms of its recognition accuracy along with the recent advances in deep machine learning, and has attracted much research attention as a promising technology that can simultaneously offer both convenience and precision. Our face recognition technology was evolving by adopting major methods of the time in three different stages: (1) distance comparison among feature points (e.g. eyebrows and nose) in 1990, (2) statistical methods such as Eigenface and FisherFace in the 2000s, and (3) recently used methods such as deep machine learning after the 2010s. NEC actively conducts researches on presentation attack detection (PAD), which aims to distinguish live face samples from spoof artifacts, for securing biometrics authentication.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
