Smart Eyewear Systems

Introduction

In this project, we extend the capability of head-mounted camera and display systems such as Google Glass. We use computer vision to automatically derive contextual information based on the images captured by camera. We then use domain-specific knowledge to provide relevant information to the user, to assist in various information retrieval tasks or to provide coaching or instruction in real-time.

Face Recognition for Prosopagnosics

Prosopagnosia, or the inability to recognize faces, is widespread around the world, with no effective cure for the disease. In this project, we built a wearable system to improve prosopagnosic's daily life. The system utilizes real-time face recognition that runs on a smartphone, and a portable eyewear that displays descriptive information when a person appears in range of camera mounted on the eyewear. The system helps these patients identify faces, reminds them to make social reactions and ultimately prevents them from developing social anxiety disorders, characterized by fear and avoidance of social situations that may cause embarrassment. We implemented this system on Vuzix camera/display eyewear system.

Publications

Xi Wang, Xi Zhao, Varun Prakash, Weidong Shi, Omprakash Gnawali, Computerized-Eyewear Based Face Recognition System For Improving Social Lives of Prosopagnosics, In 7th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth 2013), Short Paper, Venice, Italy, May 2013.

Xi Wang, Xi Zhao, Omprakash Gnawali, Katherine Loveland, Varun Prakash and Weidong Shi, Real-Time Selective Speaker Cancellation System for Relieving Social Anxiety in Autistics, In Third International Workshop on Pervasive Computing Paradigms for Mental Health (MindCare 2013), Venice, Italy, May 2013.

Last updated: May 2013