Faculty Advisor

Venkatasubramanian, Krishna Kumar

Abstract

Personalized devices often require a form of user identification to provide customized performance and rudimentary privacy between a limited amount of users. Because of the personal nature of head mounted devices, the new and growing industry of head mounted displays requires a method to identify users to increase customizability and usability of such devices. This project introduces a system that accurately identifies users with common sensors included on head mounted displays. The proposed system records user blink behavior, head position and head movement and then uses high dimensional machine learning algorithms to identify users based on trends in their collected data. The system demonstrated over 98% accuracy, demonstrating its ability to identify users.

Publisher

Worcester Polytechnic Institute

Date Accepted

March 2015

Major

Computer Science

Project Type

Major Qualifying Project

Accessibility

Unrestricted

Advisor Department

Computer Science

Share

COinS