Affiliations: [a] Department of Fundamental and Applied Sciences, Universiti Teknologi PETRONAS, 32610 Bandar Seri Iskandar, Perak, Malaysia | [b] Department of Electrical and Electronic Engineering, University of Dhaka, Dhaka, Bangladesh | [c] School of Computing, Dublin Institute of Technology, Dublin, Ireland
Correspondence:
[*]
Corresponding author: Fahad Parvez Mahdi, Department of Fundamental and Applied Sciences, Universiti Teknologi PETRONAS, 32610 Bandar Seri Iskandar, Perak, Malaysia. E-mail:fahadapecedu@gmail.com
Abstract: The ability to automatically recognize human faces based on dynamic facial images is important in security, surveillance and the health/independent living domains. Specific applications include access control to secure environments, identification of individuals at a particular place and intruder detection. This research proposes a real-time system for surveillance using cameras. The process is broken into two steps: (1) face detection and (2) face recognition to identify particular persons. For the first step, the system tracks and selects the faces of the detected persons. An efficient recognition algorithm is then used to recognize detected faces with a known database. The proposed approach exploits the Viola-Jones method for face detection, the Kanade-Lucas-Tomasi algorithm as a feature tracker and Principal Component Analysis (PCA) for face recognition. This system can be implemented at different restricted areas, such as at the office or house of a suspicious person or at the entrance of a sensitive installation. The system works almost perfectly under reasonable lighting conditions and image depths.
Keywords: Computer vision, face detection, face tracking, face recognition, real time, video surveillance, Viola and Jones, principal component analysis
