Key points are not available for this paper at this time.
In this paper, we present a pen-shaped input device forwearable computers which reproduce and recognizethree-dimensional (3D) hand motions with no externalreferences. The input device is equipped with inertialsensors. The inertial sensors measure accelerations andangular velocities produced by a user's handwritingmotion in 2D/3D spaces. The measurements fromgyroscopes are integrated once to produce the attitude ofthe system and are consequently used to remove theeffects of the gravity and the inclination of the system.The compensated acceleration measurements are doublyintegrated to yield the position of the system. Due to theintegration processes involved in reproducing thehandwriting trajectory, the accuracy of the positionmeasurement significantly deteriorates along with time.To reproduce handwriting trajectory of a stroke on asurface and even in the air, we propose algorithms tosegment a stroke, to compensate the integration errors,and to reconstruct 2D trajectory on the x-y plane from 3Dtrajectory in the air. Real experimental results areincluded to show the effectiveness and feasibility of theproposed algorithms. The proposed methods provide anew approach for implementing a small, user-friendlykeyboard alternative input device for wearable computers.
Bang et al. (Tue,) studied this question.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: