Motor Impairments Stroke-Gesture Dataset

This dataset contains 9,681 stroke-gesture samples collected from 70 participants, from which 35 participants with motor impairments.
The dataset is companion to our CHI 2019 paper Vatavu and Ungurean (2019) in which we report experimental results on stroke-gestures performed by people with and without motor impairments. For example, we found that stroke-gestures produced by people with motor impairments were recognized less accurately than the same gesture types produced by people without impairments, yet still accurately enough (93%) for practical purposes; were similar in terms of geometrical criteria to the gestures produced by people without impairments; but took considerably more time to produce (3.4s vs. 1.7s) and exhibited lower consistency in articulation (−49.7%). For more results, please see our paper.


We release our gesture dataset to encourage further studies, research, and development to understand stroke-gesture input on touchscreen devices for users with motor impairments. Our dataset and C# code are freely available to download and use for research purposes under this license.
If you find our dataset and/or code useful for your work, please let us know.
If you use our dataset and/or code to report results in scientific publications, please reference the Vatavu and Ungurean (2019) publication that introduced these resources. Thanks!



For any information or suggestion regarding this web page, the dataset, or the source code, please contact Prof. Radu-Daniel Vatavu.