Deep-Facial Feature-Based Person Re-identification for Authentication in Surveillance Applications

Nowadays, a large network of cameras is predominantly used in public places which provide enormous video data. These data are monitored manually and may be utilized only when the need arises to ascertain facts. Automating system can improve quality surveillance useful for high-level tasks like person identification, suspicious activity detection or undesirable event prediction timely alerts. In this paper, we proposed model that Re-identify from single camera tracking environment. This will automatically extract face features generate Unique Id each it enters first time area. Its stored database help whenever same appears again. The challenges faced by occlusion, pose, light conditions, orientation. highlights, effect different deep neural networks Person Re-identification compares based on accuracy, GPU usage, Speed, Number faces detected overcoming illumination occlusion. advantage doesn′t require people advance recognition helpful criminal identification crime control prevention.