Open AccessA Cost-efficient Real-time Security Surveillance System Based on Facial Recognition Using Raspberry Pi and OpenCV
Author(s) -
Jyotirmaya Ijaradar,
Jǐnjīng Xǔ
Publication year - 2022
Publication title -
current journal of applied science and technology
Language(s) - English
Resource type - Journals
ISSN - 2457-1024
DOI - 10.9734/cjast/2022/v41i531665
Subject(s) - computer science , artificial intelligence , computer vision , raspberry pi , histogram of oriented gradients , local binary patterns , face detection , facial recognition system , histogram , haar like features , identification (biology) , face (sociological concept) , pattern recognition (psychology) , image (mathematics) , computer security , social science , botany , sociology , biology , internet of things
Home surveillance systems are still challenging, particularly for patrolling or tracking subjects through CCTV images despite recent developments. Therefore, it is crucial to instantly identify human faces based on captured facial images in protection and surveillance. Identification of people, intrusion detection, and follow up access control of objective sites are examples of applications of such systems. This paper represented a cost-efficient real-time facial recognition-based surveillance system for home and small offices using raspberry pi and computer vision. In the application, first, the system tracks the detected individuals' faces in the frame and only focuses on the image content in these facial regions. Then, a powerful algorithm for recognising detected faces is used using a pre-provided face database. For the implementation in this paper, the most common Haar Cascade and Local Binary Pattern Histogram (LBPH) algorithms are used for facial detection and recognition. The system works perfectly in normal lighting conditions with accepted accuracy.