Multiple Face Detection For Surveillance Systems

Chia, Wei See (2019) Multiple Face Detection For Surveillance Systems. Project Report. Universiti Teknikal Malaysia Melaka, Melaka, Malaysia. (Submitted)

Text (24 Pages) Multiple face detection for surveillance systems.pdf - Submitted Version Download (343kB)

Abstract

Surveillance system is observing a scene by using electronic equipment such as closed-circuit television (CCTV) camera. Pan-tilt-zoom (PTZ) camera is a camera with the ability of changing the position of the scene by pan and tilt features. The downside of the camera is unable to capture the face clearly as it focuses on the static point of the lens. Thus, the goal of the project is to develop a surveillance system that is capable to detect face within the camera view. This project was developed by using LabView and Microsoft Visual Studio. The data from camera and navigation system were implemented by using LabView whereas the face detection system was done by using both LabView and Microsoft Visual Studio. The performance of the face detection was examined by conducting various kind of experiments, which include facial orientation, movement of the face, obstruction on face and light conditions. The accuracy was achieved at 89% and the system able to detect minimum 10 faces in a view of a scene.

Actions (login required)

View Item