A mirror that reflects, augments and learns

Abstract

Unlike the Magic Mirror in Snow White, waiting for users’ active requests, what if an augmented mirror was like the Mirror of Erised, capable of serving users’ implicit needs? We develop an augmented mirror system that reflects images of real-world objects by nature, collocates digitally rendered information with the reflections and learns the correlations among users, objects and augmented information. By exploring the design space, implementing an actual system, and conducting a preliminary study, we demonstrate that our system provides users needed information at the right time, thereby allowing them to make improved decisions and take appropriate actions.