In most situations, identifying humans using faces is an effortless task for humans. Is this true for computers? This very question defines the field of automatic face recognition, one of the most active research areas in computer vision, pattern recognition, and perception. Over the past two decades, the problem of face recognition has attracted substantial attention from various disciplines and has witnessed an impressive growth in basic and applied research, product development and applications. Face recognition systems have been deployed at ports of entry at international airports in Australian and Portugal. In addition, studies on human perception of faces  have resulted in many interesting findings that can be used in the design of practical systems. Besides applications related to identification and verification such as access control, law enforcement, ID and licensing, surveillance, etc., face recognition is also useful in humancomputer interaction, virtual reality, database retrieval, multimedia, computer entertainment, etc. More detailed discussions on face acquisition, processing, recognition and verification may be found in a survey paper , research monographs and recently published edited books [3, 4]. In this paper, we begin with a discussion of why automatic face recognition is hard, present a brief review of the past two decades of work in face recognition and then present a brief outline of future research trends.
, Chellappa, R.
and Sinha, P.
Face Recognition by Computers and Humans, Computer (IEEE Computer), [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=903088
(Accessed December 8, 2023)