Environmental effects on face recognition in smartphones

Abstract

Face recognition is convenient for user authentication on smartphones as it offers several advantages suitable for mobile environments. There is no need to remember a numeric code or password or carry tokens. Face verification allows the unlocking of the smartphone, pay bills or check emails through looking at the smartphone. However, devices mobility also introduces a lot of factors that may influence the biometric performance mainly regarding interaction and environment. Scenarios can vary significantly as there is no control of the surroundings. Noise can be caused by other people appearing on the background, by different illumination conditions, by different users' poses and through many other reasons. User-interaction with biometric systems is fundamental: bad experiences may derive to unwillingness to use the technology. But how does the environment influence the quality of facial images? And does it influence the user experience with face recognition? In order to answer these questions, our research investigates the user-biometric system interaction from a non-traditional point of view: we recreate real-life scenarios to test which factors influence the image quality in face recognition and, quantifiably, to what extent. Results indicate the variability in face recognition performance when varying environmental conditions using smartphones.