Abstract:
In developing countries, traditional access
management systems ubiquitously use either keypad based
password protection or radio frequency identification (RFID)
card based protection. With the increased number of threats in
recent years, these systems are becoming more vulnerable. If
the password or the RFID card is somehow compromised, any
unauthorized person can breach the system with ease.
Considering and analyzing these issues, a cost-effective
prototype of a vision based three-layer access management
system with IoT connectivity was developed. In this paper, an
access management system architecture is proposed based on
the fusion of radio frequency identification, back propagation
based face recognition and password protection. The system is
also connected to a Node JS based web server. Whenever an
access is granted or any unauthorized access is detected, an
SMS and an email are sent to both the user and the system
administrator. Data security is ensured by exploiting AES
encryption on the system side and AES decryption on the
server side. In case of face recognition, the access is granted if
the achieved confidence level is over 80%.
