Facial recognition using human visual system algorithms for robotic and UAV platforms

摘要

In this paper we present a low-cost facial recognition system using a commercial off-the-shelf (COTS) unmanned aerial vehicle (UAV) platform to capture images and video. Our novel approach produces real-time accurate detection and recognition of key features allowing the system to be used in real world security applications. We present recognition algorithms that enable the system to perform quality recognition with a minimal training set. The system can be used in other robotic platforms. It is highly modular and adaptable to other systems.