标题:Combining Features for Chinese Sign Language Recognition with Kinect
作者:Geng, Lubo; Ma, Xin; Xue, Bingxia; Wu, Hanbo; Gu, Jason; Li, Yibin
通讯作者:Ma, X
作者机构:[Geng, Lubo; Ma, Xin; Xue, Bingxia; Wu, Hanbo; Li, Yibin] Shandong Univ, Sch Control Sci & Engn, Jinan 250100, Shandong, Peoples R China.; [Gu, Jaso 更多
会议名称:11th IEEE International Conference on Control and Automation (ICCA)
会议日期:JUN 18-20, 2014
来源:11TH IEEE INTERNATIONAL CONFERENCE ON CONTROL AND AUTOMATION (ICCA)
出版年:2014
页码:1393-1398
DOI:10.1109/ICCA.2014.6871127
关键词:spherical coordinate system; 3D trajectory; ELM; sign language; recognition
摘要:In this paper, we propose a novel three-dimensional combining features method for sign language recognition. Based on the Kinect depth data and the skeleton joints data, we acquire the 3D trajectories of right hand, right wrist and right elbow. To construct feature vector, the paper uses combining location and spherical coordinate feature representation. The proposed approach utilizes the feature representation in spherical coordinate system effectively depicting the kinematic connectivity among hand, wrist and elbow for recognition. Meanwhile, 3D trajectory data acquired from Kinect avoid the interference of the illumination change and cluttered background. In experiments with a dataset of 20 gestures from Chinese sign language, the Extreme Learning Machine(ELM) is tested, compared with Support Vector Machine(SVM), the superior recognition performance is verified.
收录类别:CPCI-S;EI;SCOPUS
WOS核心被引频次:7
Scopus被引频次:10
资源类型:会议论文;期刊论文
原文链接:https://www.scopus.com/inward/record.uri?eid=2-s2.0-84906535853&doi=10.1109%2fICCA.2014.6871127&partnerID=40&md5=453107e3426b49f0e52667cc6d3d1203
TOP