A new artificial intelligence (AI) technique developed by computer scientists at ETH Zurich more precisely estimates where a finger touches a mobile phone screen, to reduce typing errors.
ETH's Christian Holz explained the CapContact AI “estimates the actual contact areas between fingers and touchscreens upon touch,” then “generates these contact areas at eight times the resolution of current touch sensors, enabling our touch devices to detect touch much more precisely."
The researchers found their novel deep learning approach eliminates low-resolution input sensing errors, which they said are responsible for a third of errors on current touchscreen devices.
From ETH Zurich (Switzerland)
View Full Article
Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA