Realtime Intrusion Detection System Using Open CV

Abstract

Security in restricted areas is essential for protecting valuable assets, sensitive information, ensuring the safety of personnel from intruders. Traditional security systems have many limitations, where they cannot authenticate whether the entered person is an intruder or not. Authentication of the entered person can be done by face identification, through which a smart security system can be developed. Creating and implementing a face recognition-based surveillance system is the goal of this project. Realtime Intrusion detection system provides surveillance for restricted and confidential areas with help of face recognition and detection, when an intruder or unauthorized person enters the area, this system will give an alert to the respective in charge or buzzer an intrusion alarm. Facial recognition is a method of recognising an individual. In this system, the OpenCV python library along with several algorithms are used to abstract the facial features and to take the input dataset. For face recognition, LBPH algorithm is used. With help of this technique, we can ensure whether the entered person is an intruder or an authorized one. Accuracy of the face recognition is 94.5%. A GUI (graphical user interface) is developed for ease of accessibility with the help of python tkinter.