Visual gesture recognition

Author

Davis, J. ; Shah, M.

Author_Institution

Comput. Vision Lab., Central Florida Univ., Orlando, FL, USA

Volume

141

Issue

2

fYear

1994

fDate

4/1/1994 12:00:00 AM

Firstpage

101

Lastpage

106

Abstract

Presents a method for recognising human-hand gestures using a model based approach. A finite state machine is used to model four qualitatively distinct phases of a generic gesture. Fingertips are tracked in multiple frames to compute motion trajectories. The trajectories are then used for finding the start and stop position of the gesture. Gestures are represented as a list of vectors and are then matched to stored gesture vector models using table lookup based on vector displacements. Results are presented showing recognition of seven gestures using images sampled at 4 Hz on a SPARC-1 without any special hardware. The seven gestures are representatives for actions of left, right, up, down, grab, rotate, and stop

Keywords

finite state machines; image recognition; image sequences; motion estimation; parameter estimation; table lookup; down; fingertips; finite state machine; generic gesture; grab; human-hand gestures; left; model based approach; motion trajectories; multiple frames; recognition; right; rotate; start position; stop; stop position; stored gesture vector models; table lookup; up; vector displacements; visual gesture recognition;

fLanguage

English

Journal_Title

Vision, Image and Signal Processing, IEE Proceedings -

Publisher

iet

ISSN

1350-245X

Type

jour

DOI

10.1049/ip-vis:19941058

Filename

285834