ResType: Invisible and Adaptive Tablet Keyboard Leveraging Resting Fingers

要旨

Text entry on tablet touchscreens is a basic need nowadays. Tablet keyboards require visual attention for users to locate keys, thus not supporting efficient touch typing. They also take up a large proportion of screen space, which affects the access to information. To solve these problems, we propose ResType, an adaptive and invisible keyboard on three-state touch surfaces (e.g. tablets with unintentional touch prevention). ResType allows users to rest their hands on it and automatically adapts the keyboard to the resting fingers. Thus, users do not need visual attention to locate keys, which supports touch typing. We quantitatively explored users' resting finger patterns on ResType, based on which we proposed an augmented Bayesian decoding algorithm for ResType, with 96.3% top-1 and 99.0% top-3 accuracies. After a 5-day evaluation, ResType achieved 41.26 WPM, outperforming normal tablet keyboards by 13.5% and reaching 86.7% of physical keyboards. It solves the occlusion problem while maintaining comparable typing speed with current methods on visible tablet keyboards.

著者
Zhuojun Li
Tsinghua University, Beijing, China
Chun Yu
Tsinghua University, Beijing, China
Yizheng Gu
Department of Computer Science and Technology, Tsinghua University, Beijing, China
Yuanchun Shi
Tsinghua University, Beijing, China
論文URL

https://doi.org/10.1145/3544548.3581055

動画

会議: CHI 2023

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2023.acm.org/)

セッション: Text Input and Textual Communication

Room Y05+Y06
6 件の発表
2023-04-27 18:00:00
2023-04-27 19:30:00