Recognizing Humans without Face Recognition


    Wearable cameras and displays, such as the Google Glass, are around the corner. This work explores techniques that jointly leverage camera-enabled glasses and smartphones to recognize individuals in the visual surrounding. While face recognition would be one approach to this problem, we believe that it may not be always possible to see a person's face. Our technique is complementary to face recognition, and exploits the intuition that colors of clothes, decorations, and even human motion patterns, can together make up a "fingerprint". Such a fingerprint could be effectively used towards human recognition or content announcement in the visual vicinity, and more broadly towards enabling human-centric augmented reality. Pivoted on this vision, we develop a proof of concept system called InSight to recognize individuals. Our paper on InSight is presented at HotMobile 2013.


InSight received wide coverage in the popular media. Here is a representative list of articles.


Cnet     Engadget     Los Angeles Times     San Francisco Chronicle     Bangkok Post     NewScientist     Slate     Mobile Magazine     ZDNet     TechCrunch     Association for Computing Machinery     Information Week     PCWorld     Gizmodo     Yahoo! Finance     TheVerge     Gizmag     Fast Company     Business Insider     RT     The Register     Ubergizmo     Sina Tech     Yahoo! Japan     Latinos Post     Digital Journal