Abstract
Face recognition is a biometric which is attracting significant research, commercial and government interest, as it provides a discreet, non-intrusive way of detecting, and recognizing individuals, without need for the subject's knowledge or consent. This is due to reduced cost, and evolution in hardware and algorithms which have improved their ability to handle unconstrained conditions. Evidently affordable and efficient applications are required. However, there is much debate over which methods are most appropriate, particularly in the context of the growing importance of deep neural network-based face recognition systems. This systematic review attempts to provide clarity on both issues by organizing the plethora of research and data in this field to clarify current research trends, state-of-the-art methods, and provides an outline of their benefits and shortcomings. Overall, this research covered 1,330 relevant studies, showing an increase of over 200% in research interest in the field of face recognition over the past 6 years. Our results also demonstrated that deep learning methods are the prime focus of modern research due to improvements in hardware databases and increasing understanding of neural networks. In contrast, traditional methods have lost favor amongst researchers due to their inherent limitations in accuracy, and lack of efficiency when handling large amounts of data.
Abstract (translated)
URL
https://arxiv.org/abs/1908.04404
