Researchers from the Arizona State University have developed an air-handwriting/tracing tool, an open research infrastructure called FMKit for in-air handwriting analysis.
The FMKit is comprised of a set of Python libraries and a data repository collected from more than 180 users with two different types of motion capture sensors.
Two different device types are used to capture hand movement, using a leap motion controller and a custom-made data glove with an inertial measurement unit (IMU) at the tip of the index finger, capable of captured the 3D position of each joint of the hand at approximately 110 Hz.
The data glove can track the 3D acceleration and angular speed of the tip of the index finger at 50Hz.
A Python module (programming language) is constructed to obtain other physical states including orientation and can conduct other pre-processing such as resampling, posture normalisation and filter. A Python-based data browser is also built in to allow for the inspection and visualisation of signals.
The system can be used to create ‘meaningful strings’ with their fingers as ID-passcodes, containing characters and symbols (such as stars) that cannot be typed, with this system also able to be used for user identification.
In a report, titled ‘
FMKit – An In Air-Handwriting Analysis Library and Data Repository’, researchers Duo Lu, Linzhen Luo, Dijiang Huang and Yezhou Yang, Arizona State University, said: "Hand-gesture and in-air-handwriting provide ways for users to input information in Augmented Reality (AR) and Virtual Reality (VR) applications where a physical keyboard or a touch screen is unavailable. However, understanding the movement of hands and fingers is challenging, which requires a large amount of data and data-driven models…
"“The construction of FMKit is work-in-progress and we hope it can help other research work in this area and pave the road to practical usage of in-air-handwriting as an input method.”