GestureCommander
George Lucchese, Martin Field, Jimmy Ho, Ricardo Gutiérrez‐Osuna, Tracy Hammond · 2012
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.