Abstract
Internet of Things (IoT)-enabled intelligent systems are proliferating rapidly,
providing the capability to connect virtually any device to the Internet. Consequently,
this concept can be effectively utilized in home security applications. In this paper, we
have introduced an IoT-enabled system designed to send security alerts to users via
email upon detecting human intrusion. The system comprises a PIR sensor, Pi camera,
Raspberry Pi-3, and an Internet connection. There are two operational modes in the
proposed security system. In the first mode, movement by an intruder is detected, and
simultaneously, every time someone rings the doorbell, the Pi camera captures an
image. The system then accesses a stored database to ascertain whether the individual
is recognized. If the person is unfamiliar, the user receives an email notification,
including the captured image of the individual. On the other hand, if the person is
recognized, the system stores the captured image. In the second mode, when someone
exhibits suspicious behaviour in front of the door, the system sends an alert email to the
user, prompting them to activate the security alert system installed at the entrance. For
face detection, we employ the Haar cascade technique. Face recognition involves two
steps: feature extraction and classification. In the feature extraction phase, we compare
various algorithms, and a comparative study of these provides a methodology that
achieves 99.56% accuracy, outperforming other existing models. The developed
system leverages the IoT platform to fortify security against intruders, thereby fostering
a safe and secure environment.
Keywords: Face recognition, Home security system, Internet of things.