The case of face recognition on mobile devices

Abstract

Smartphones have become the most convenient and ubiquitous interface for Internet services. They are equipped with a multitude of sensors that can significantly improve the user's cognitive ability. Face recognition is one of the fastest growing applications in mobile domains due to the wide range of potential uses. However, face recognition is a computation-intensive process and requires resources beyond the capacity of even modern mobile devices. In this paper, we present an efficient facial recognition approach based on cloud computation offloading. The architecture performs initial image processing on the mobile devices to reduce the network traffic and save battery power before offloading the recognition to the cloud. Preliminary results show more than 230% reduction in the overall response time and over 200% energy savings on the mobile device.