Effect of computation offload on performance and energy consumption of mobile face recognition

Abstract

Computation offloading is a paramount technology to leverage network resources for mobile devices. This paper studies effect of computation offloading on efficiency of mobile face recognition. It compares offloading alternatives used in existing mobile face-recognition system and reports on their efficiency in terms of energy consumption, processing time and recognition accuracy. The offloading method which leads to the best energy-performance tradeoff is outlined.