A Vision Based Three-Layer Access Management System with IoT Integration

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%.