GestureCommander: continuous touch-based gesture prediction

Authors:
George Lucchese;Martin Field;Jimmy Ho;Ricardo Gutierrez-Osuna;Tracy Hammond
Affiliations:
Texas A&M University, College Station, Texas, USA;Texas A&M University, College Station, Texas, USA;Texas A&M University, College Station, Texas, USA;Texas A&M University, College Station, Texas, USA;Texas A&M University, College Station, Texas, USA
Venue:
CHI '12 Extended Abstracts on Human Factors in Computing Systems
Year:
2012

Citing 8
Cited 2

Specifying gestures by example

Proceedings of the 18th annual conference on Computer graphics and interactive techniques
The limits of expert performance using hierarchic marking menus

INTERCHI '93 Proceedings of the INTERCHI '93 conference on Human factors in computing systems
Gestures without libraries, toolkits or training: a $1 recognizer for user interface prototypes

Proceedings of the 20th annual ACM symposium on User interface software and technology
PaleoSketch: accurate primitive sketch recognition and beautification

Proceedings of the 13th international conference on Intelligent user interfaces
OctoPocus: a dynamic guide for learning gesture-based command sets

Proceedings of the 21st annual ACM symposium on User interface software and technology
Scale detection for a priori gesture recognition

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Protractor: a fast and accurate gesture recognizer

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
A lightweight multistroke recognizer for user interface prototypes

Proceedings of Graphics Interface 2010

Beyond recognition: using gesture variation for continuous interaction

CHI '13 Extended Abstracts on Human Factors in Computing Systems
Technical Section: Recognition and autocompletion of partially drawn symbols by using polar histograms as spatial relation descriptors

Computers and Graphics

Quantified Score

Hi-index	0.00

Visualization

Abstract

GestureCommander is a touch-based gesture control system for mobile devices that is able to recognize gestures as they are being performed. Continuous recognition allows the system to provide visual feedback to the user and to anticipate user commands to possibly decrease perceived response time. To achieve this goal we employ two Hidden Markov Model (HMM) systems, one for recognition and another for generating visual feedback. We analyze a set of geometric features used in other gesture recognition systems and determine a subset that works best for HMMs. Finally we demonstrate the practicality of our recognition HMMs in a proof of concept mobile application for Google's Android mobile platform that has a recognition accuracy rate of 96% over 15 distinct gestures.