Design Methodology for Face Detection Acceleration

Abstract

A design methodology to accelerate the face detection for embedded systems is described, starting from high level (algorithm optimization) and ending with low level (software and hardware codesign) by addressing the issues and the design decisions made at each level based on the performance measurements and system limitations. The implemented embedded face detection system consumes very little power compared with the traditional PC software implementations while maintaining the same detection accuracy. The proposed face detection acceleration methodology is suitable for real time applications