Gesture typing is a popular text input method used on smartphones. Gesture keyboards are based on word gestures that subsequently trace all letters of a word on a virtual keyboard. Instead of tapping a word key by key, the user enters a word gesture with a single continuous stroke. In this paper, we introduce an implicit user verification approach for short text messages that are entered with a gesture keyboard. We utilize the way people interact with gesture keyboards to extract behavioral biometric features. We propose a proof-of-concept classification framework that learns the gesture typing behavior of a person and is able to decide whether a gestured message was written by the legitimate user or an imposter. Data collected from gesture keyboard users in a user study is used to assess the performance of the classification framework, demonstrating that the technique has considerable promise.
In this paper we present DigiTap-a wrist-worn device specially designed for symbolic input in virtual and augmented reality (VR/AR) environments. DigiTap is able to robustly sense thumb-to-finger taps on the four fingertips and the eight minor knuckles. These taps are detected by an accelerometer, which triggers capturing of an image sequence with a small wrist-mounted camera. The tap position is then extracted with low computational effort from the images by an image processing pipeline. Thus, the device is very energy efficient and may potentially be integrated in a smartwatch-like device, allowing an unobtrusive, always available, eyes-free input. To demonstrate the feasibility of our approach an initial user study with our prototype device was conducted. In this study the suitability of the twelve tapping locations was evaluated, and the most prominent sources of error were identified. Our prototype system was able to correctly classify 92 % of the input locations.
Thumb-to-finger tap interaction can be employed to perform eyes-free, discrete, symbolic input in virtual and augmented reality environments. The DigiTap device is worn on the wrist to keep the hand free from any instrumentation so as not to impair tactile sense and dexterity. DigiTap senses the jerk that is caused by a tap and takes an image sequence to detect the tap location. The device can recognize taps at 12 different locations on the fingers, and at some positions, it can even distinguish between different tap strengths. The authors conducted an extended user study to evaluate users' abilities to interact with the device and perform symbolic input.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.