Speed optimized face recognition on mobile devices using Eigenfaces decomposition

Abstract

Face recognition on mobile devices can be utilized for security applications (e.g., user authentication) or in the context of pervasive and assistive computing for the support of elderly suffering from dementia in recognizing persons or for the development of cognitive memory games. This paper initially presents the design of intelligent systems for analyzing and performing face recognition, discussing the state of the art in the field and providing the necessary background information. At a second stage the paper describes the development and technical details of a speed-optimized face recognition system for mobile devices. The proposed methodology is based on Eigenfaces decomposition and Mahalanobis distance calculation applied on captured face images, while the mobile application has been developed for the Android OS. The initial implementation and the corresponding results have proven the feasibility and value of the proposed system. © 2010 CRL Publishing Ltd.