Magic wand: a hand-drawn gesture input device in 3-D space with inertial sensors

Author

Cho, Sung-Jung ; Oh, Jong Koo ; Bang, Won-Chul ; Chang, Wook ; Choi, Eunseok ; Jing, Yang ; Cho, Joonkee ; Kim, Dong Yoon

Author_Institution

Samsung Adv. Inst. of Technol., Suwon, South Korea

fYear

2004

fDate

26-29 Oct. 2004

Firstpage

106

Lastpage

111

Abstract

This paper presents a gesture input device, magic wand, with which a user can input gestures in 3-D space, inertial sensors embedded in it generate acceleration and angular velocity signals according to a user´s hand movement. A trajectory estimation algorithm is employed to convert them into a trajectory on 2-D plane. The recognition algorithm based on Bayesian networks finds the gesture model with the maximum likelihood from it. The recognition performance of the proposed system is quite promising; the writer-independent recognition rate was 99.2% on average for the database of 15 writers and 13 gesture classes.

Keywords

belief networks; gesture recognition; handwriting recognition; handwritten character recognition; interactive devices; maximum likelihood detection; Bayesian network; acceleration signal; angular velocity signal; hand drawn gesture input device; inertial sensor; magic wand; maximum likelihood detection; trajectory estimation; user hand movement; Acceleration; Accelerometers; Angular velocity; Bayesian methods; Gyroscopes; Handwriting recognition; Optical surface waves; Space technology; Ultrasonic variables measurement; Writing; Accelerometer; Bayesian networks; Gesture input device; Gyroscope; Handwriting recognition; Inertial navigation system; Trajectory estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Frontiers in Handwriting Recognition, 2004. IWFHR-9 2004. Ninth International Workshop on

ISSN

1550-5235

Print_ISBN

0-7695-2187-8

Type

conf

DOI

10.1109/IWFHR.2004.66

Filename

1363895