Probabilistic adjustment of dwell time for eye typing

Requiring a dwell time before selection is a common way to solve “Midas-touch problem” in gaze-based interaction. Choosing the dwell time involves a tradeoff between unintentional selection for short dwell times and slow text entry for long dwell times. We propose a probabilistic model for gaze based selection, which adjusts the dwell time based on the probability of each letter based on the past letters selected. By reformulating the entire problem of gaze-based selection probabilistically, we can naturally integrate the probability of each character naturally and with very few prior assumptions and very few free parameters. It automatically assigns shorter dwell times to more likely characters and longer dwell times to less likely characters. Our experimental results demonstrate that the proposed technique speeds up typing without loss in accuracy. The concept of this can be generalized to other dwell-based applications, leading to more efficient gaze system interaction.

[1]  William W. Abbott,et al.  Gaze-based teleprosthetic enables intuitive continuous control of complex robot arm use: Writing & drawing , 2016, 2016 6th IEEE International Conference on Biomedical Robotics and Biomechatronics (BioRob).

[2]  Carlos Hitoshi Morimoto,et al.  AugKey: Increasing Foveal Throughput in Eye Typing with Augmented Keys , 2016, CHI.

[3]  Oleg Spakov,et al.  On-line adjustment of dwell time for target selection by gaze , 2004, NordiCHI '04.

[4]  Per Ola Kristensson,et al.  The potential of dwell-free eye-typing for fast assistive gaze communication , 2012, ETRA.

[5]  Chonho Lee,et al.  GazeTry: Swipe Text Typing Using Gaze , 2015, OZCHI.

[6]  I. Scott MacKenzie,et al.  Auditory and visual feedback during eye typing , 2003, CHI Extended Abstracts.

[7]  Alan F. Blackwell,et al.  Dasher—a data entry interface using continuous gestures and language models , 2000, UIST '00.

[8]  Oleg Spakov,et al.  Fast gaze typing with an adjustable dwell time , 2009, CHI.

[9]  Anke Huckauf,et al.  Alternatives to single character entry and dwell time selection on eye typing , 2010, ETRA.

[10]  Margrit Betke,et al.  EyeSwipe: Dwell-free Text Entry Using Gaze Paths , 2016, CHI.

[11]  Poika Isokoski,et al.  Now Dasher! Dash away!: longitudinal study of fast text entry by Eye Gaze , 2008, ETRA.

[12]  S. Hart,et al.  Development of NASA-TLX (Task Load Index): Results of Empirical and Theoretical Research , 1988 .

[13]  Meredith Ringel Morris,et al.  Improving Dwell-Based Gaze Typing with Dynamic, Cascading Dwell Times , 2017, CHI.

[14]  Steffen Staab,et al.  GazeTheKey: Interactive Keys to Integrate Word Predictions for Gaze-based Text Entry , 2017, IUI Companion.

[15]  I. Scott MacKenzie,et al.  Eye typing using word and letter prediction and a fixation algorithm , 2008, ETRA.

[16]  Päivi Majaranta,et al.  Text Entry by Eye Gaze , 2009 .

[17]  Maria da Graça Campos Pimentel,et al.  Filteryedping: Design Challenges and User Performance of Dwell-Free Eye Typing , 2015, TACC.

[18]  I. Scott MacKenzie,et al.  Metrics for text entry research: an evaluation of MSD and KSPC, and a new unified error metric , 2003, CHI '03.

[19]  Kari-Jouko Räihä,et al.  An exploratory study of eye typing fundamentals: dwell time, text entry rate, errors, and workload , 2012, CHI.

[20]  Chern-Sheng Lin,et al.  Powered Wheelchair Controlled by Eye-Tracking System , 2006 .

[21]  I. Scott MacKenzie,et al.  Phrase sets for evaluating text entry techniques , 2003, CHI Extended Abstracts.

[22]  Worthy N. Martin,et al.  Human-computer interaction using eye-gaze input , 1989, IEEE Trans. Syst. Man Cybern..

[23]  Jacob O. Wobbrock,et al.  Longitudinal evaluation of discrete consecutive gaze gestures for text entry , 2008, ETRA.