Real-time hand gesture feature extraction using depth data

Research output: Chapter in Book/Report/Conference proceedingConference contribution

158 Downloads (Pure)

Abstract

In this paper, a novel method is proposed to extract hand gesture features in real-time from RGB-D images captured by the Microsoft's Kinect. A contour length information based de-noise method is introduced for the hand gesture smooth segmentation and edge contour extraction. In addition, a finger earth mover's distance algorithm is applied with a novel approach to locate the palm image and extract fingertip features. Especially the proposed Lasso algorithm can effectively extract the fingertip feature from a hand contour curve correctly with excellent real-time performance.
Original languageEnglish
Title of host publicationProceedings of the 2014 International Conference on Machine Learning and Cybernetics (ICMLC)
PublisherIEEE
Pages206-213
ISBN (Electronic)978-1-4799-4215-2
ISBN (Print)978-1-4799-4216-9, 978-1-4799-4214-5
DOIs
Publication statusPublished - 15 Jan 2015
Event2014 International Conference on Machine Learning and Cybernetics - Lanzhou, China
Duration: 13 Jul 201416 Jul 2014

Publication series

Name
ISSN (Print)2160-133X

Conference

Conference2014 International Conference on Machine Learning and Cybernetics
Abbreviated titleICMLC 2014
Country/TerritoryChina
CityLanzhou
Period13/07/1416/07/14

Fingerprint

Dive into the research topics of 'Real-time hand gesture feature extraction using depth data'. Together they form a unique fingerprint.

Cite this