Date of Award
6-1-2016
Document Type
Thesis (Undergraduate)
Department or Program
Department of Computer Science
First Advisor
Xing-Dong Yang
Abstract
The human body is full of electrical signals. We propose to use the electric signals produced by the human body to input text without the use of a physical keyboard. We allow users to tap their fingers in the air as if typing on an imaginary keyboard. To detect the tapping, we created a wearable armband that uses electromyography (EMG) sensors to track individual finger muscle activation. Each finger is mapped to several characters, and based on the finger-sequence the user taps, a list of possible typed words is presented. Augmented reality and virtual reality headsets are becoming more prevalent (Oculus Rift, Microsoft Hololens, Google Cardboard, Magic Leap), and yet none of the existing typing techniques allow the user to easily input text while using these devices away from a desk. Giving users the ability to input text without using a physical keyboard opens up the possibility of using AR or VR in any location. We discuss the challenges in making our initial prototype more practical, robust, and reliable as part of our on-going research.
Recommended Citation
Gaba, Jacob A., "Air Keyboard: Mid-Air Text Input Using Wearable EMG Sensors and a Predictive Text Model" (2016). Dartmouth College Undergraduate Theses. 114.
https://digitalcommons.dartmouth.edu/senior_theses/114
Comments
Originally posted in the Dartmouth College Computer Science Technical Report Series, number TR2016-809.