HMM-based gesture recognition for eye-swipe typing

Abstract

Eye-swipe typing requires users to simply look in the vicinity of the keys forming the desired word, similar to swiping their finger on a touch screen device. This work presents a novel HMM-based approach for swipe typing which can be used with any eye movement recording technique. In this study, three different HMM-based methods are developed, tested, and compared to the state-of-the-art performing LCSMapping algorithm with eye movement data acquired from the electrooculogram (EOG). When tested by ten subjects, the top performing Key-based HMM yielded an average top-five rate of 91.00±6.63% in comparison to an average top-five rate of 76.00±12.61% achieved by the LCSMapping algorithm. This study also presents the analysis of a real-time eye controlled swipe typing application which yielded an average typing speed of 12.85±2.14 WPM in contrast to an average typing speed of 3.83±1.24 WPM achieved using a dwell-based alternative.