BibTex
@inproceedings{Liu:2019:10.20380/GI2019.09,
author = {Liu, Qi Feng and Katsuragawa, Keiko and Lank, Edward},
title = {Eliciting Wrist and Finger Gestures to Guide Recognizer Design},
booktitle = {Proceedings of Graphics Interface 2019},
series = {GI 2019},
year = {2019},
issn = {0713-5424},
isbn = {978-0-9947868-4-5},
location = {Kingston, Ontario},
numpages = {9},
doi = {10.20380/GI2019.09},
publisher = {Canadian Information Processing Society},
}
Abstract
While hand gestures, i.e. movements of the fingers and wrist, are a low-effort input modality, sensing and recognition of these smallscale gestures is challenging. In particular, while many authors have explored varying designs of hardware to support hand gesture input, each systems recognize their own gesture set, rendering challenging comparisons between different capture and recognition systems. In this paper, we explore the design of hand and finger gesture input by conducting an elicitation study to understand the tradeoffs between hand, wrist, and arm gestures. Alongside this, to evaluate the overall potential of wrist-worn recognition, we explore the design of hardware to recognize gestures by contrasting an IMUonly recognizer with a simple low-cost wrist-flex sensor. We discuss the implications of our work both to the comparative evaluation of systems and to the design of enhanced hardware sensing.