Probabilistic touchscreen keyboard incorporating gaze point information

Abstract

We propose a novel probabilistic keyboard that takes into account the distance between a gaze point and a touch position in order to improve typing efficiency. The proposed keyboard dynamically changes the size of the search space for predicting candidate words based on a model that estimates the magnitude of touch position errors according to the distance between the gaze point and the touch position. This makes it possible for users to type intended words even when they glance at different areas on the screen. Performance was evaluated in terms of input accuracy in total error rate (TER) and of typing speed in words per minute (WPM). The results showed that the proposed keyboard successfully reduced the TER by 18.2% and increased WPM by 12.7% compared to the conventional keyboard.

Probabilistic Touchscreen Text Entry Method Incorporating Gaze Point Information

“…The touch precision decreases under these tsukato@mail.doshisha.ac.jp circumstances because users cannot recognize the key positions accurately. We measured the touch position error from a target associated with the gaze point quantitatively, and we found the variance of the touch position error increases in accordance with the distance between the gaze point and the touch target [9].…”

“…In this paper, we propose a novel probabilistic text entry method incorporating a model that estimates the magnitude of the touch position error according to the distance between the gaze point and the touch position (hereinafter referred to as the "gaze-touch model") [9]. The size of the search space for candidate words changes dynamically in association with the touch position error estimated by the gaze-touch model.…”

Gaze Gestures and Their Applications in human-computer interaction with a head-mounted display

“…Regarding interaction, because humans can freely control their eye movements, eye-tracking technology can be used as a method for HCI. For example, gaze duration has been used to determine whether a human wants to press a button on the screen or to click a pointer on the screen via eye movements [17], [18], [19], [20], [21], [22], [23]. In recent years, HCI research based on gaze gestures has emerged.…”