Symbiotic Interfaces for Wearable Face Recognition

Brad Singletary and Thad Starner

Proceedings of HCII2001 Workshop On Wearable Computing, New Orleans, LA, August 2000. to appear.

We introduce a wearable face detection method that exploits constraints in face scale and orientation imposed by the proximity of participants in near social interactions. Using this method we describe a wearable system that perceives ``social engagement,'' i.e., when the wearer begins to interact with other individuals. One possible application is improving the interfaces of portable consumer electronics, such as cellular phones, to avoid interrupting the user during face-to-face interactions. Our experimental system proved $>90$\% accurate when tested on wearable video data captured at a professional conference. Over three hundred individuals were captured, and the data was separated into independent training and test sets. A goal is to incorporate user interface in mobile machine recognition systems to improve performance. The user may provide real-time feedback to the system or may subtly cue the system through typical daily activities, such as turning to face a speaker, as to when conditions for recognition are favorable.

Keywords: context awareness face recognition wearable computing symbiotic interfaces
Postscript     Abstract     PDF     Request hardcopy

Back to technical reports