Venkatasubramanian, Krishna Kumar
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.
Worcester Polytechnic Institute
Major Qualifying Project
All authors have granted to WPI a nonexclusive royalty-free license to distribute copies of the work, subject to other agreements. Copyright is held by the author or authors, with all rights reserved, unless otherwise noted.