A vehicle surveillance system for face detection

Abstract

Face detection is the process of locating the position where faces are present in an image. Not all proposed face detection methods are suitable for direct hardware implementation. This paper proposes an improved skin-color based face detect method and outlines its transition from a software to hardware-based implementation. The hardware implementation of the face detect algorithm is examined by the FPGA (ALTERA CYCLONE EP1C6, field programmable gate arrays). Results show that it is robust to challenges of cluttered backgrounds, partial occlusion and varying illuminations. Its high detection and tracking performance makes it quite suitable for real-time applications, especially for power-limited devices, such as video surveillance systems for automated security, environment, transportation and health-care monitoring applications.