ABSTRACT
ADVANCEMENT IN FACIAL RECOGNITION SYSTEMS
Biometrics industry especially facial recognition technology has
continued to gain more importance in recent years due to its
security, Health, Finance and Consumer Electronics industries.
This paper aims at reviewing recent developments of facial
recognition systems; however, the concentration is made on the
application of deep learning approaches, advanced algorithms, and
better hardware systems. The advent of CNNs and DNNs, the
recognition of face images has moved from a slow pace to a faster
one and at the same time more accurate. These systems have
brought ability to better recognize the subject consistently, not just
in low light, from different angles or even under partial occlusion.
Nevertheless, increasing dilemmas of ethical issues and privacy
are still seen since this technology has already starting gaining
popularity. This paper also discusses the limitations of the work
that is still present, namely the dataset bias and vulnerability to
spoofing. Taken collectively, the research indicates that facial
recognition technology has come a long way but there is a need to
press on with development to overcome current shortcomings and
promote the proper use of the technology.
