The server is under maintenance between 08:00 to 12:00 (GMT+08:00), and please visit later.
We apologize for any inconvenience caused
Login  | Sign Up  |  Oriprobe Inc. Feed
China/Asia On Demand
Journal Articles
Bookmark and Share
Research on Similar Hand Gesture Recognition Based on 3D Trajectories
Pages: 49-54
Year: Issue:  3
Journal: Journal of Wuyi University(Natural Science Edition)

Keyword:  gesture recognitionhuman-computer interactiongesture segmentationHidden Markov Model;
Abstract: In order to solve the problem of low similar gesture recognition rate in dynamic hand gesture recognition, this study develops a dynamic hand gesture recognition system based on the Leap Motion equipment. After pretreatment of all the collected 3D motion trajectory data, non-similar and similar gestures are distinguished by the HMM model, using motion angles as fixed features. For similar gestures, a secondary recognition system is designed based on corner points, sub area percentage, angular point number percentage, and the track region length to width ratio. Experiments show that the final similar gesture recognition rate is as high as 92.56% and the rate of second time recognition is 17% higher than that of the first-time.
Related Articles
No related articles found