Paper Info
Title
An Isolated Sign Language Recognition System Using RGB-D Sensor with Sparse Coding
Abstract
An isolated sign language recognition system is presented in this paper. A RGB-D sensor, Microsoft Kinect, is used for obtaining color stream and skeleton points from the depth stream. For a particular sign we extract a representative feature vector composed by hand trajectories and hand shapes. A sparse dictionary learning algorithm, Label Consistent K-SVD (LC-KSVD), is applied to obtain a discriminative dictionary. Based on that, we further develop a new classification approach to get better result. Our system is evaluated on 34 isolated Chinese sign words including one-handed signs and two-handed signs. Experimental results show the proposed system gets high recognition accuracy, of the reported 96.75%, and obtain an average accuracy of 92.36% for signer independent recognition.
Year
DOI
Venue
2014
10.1109/CSE.2014.38
C3S2E
Keywords
Field
DocType
hand shape,skeleton point,recognition accuracy,representative feature vector,image coding,signer independent recognition,sparse dictionary learning algorithm,label consistent k-svd,learning (artificial intelligence),color stream,isolated sign language recognition system,sparse coding,depth stream,hand trajectory,rgb-d sensor,feature extraction,image classification,one-handed sign,discriminative dictionary,classification approach,classification,natural language processing,lc-ksvd,chinese sign word,microsoft kinect,sign language recognition,image colour analysis,isolated sign language recognition,two-handed sign,scientific computing
Computer vision,Feature vector,Dictionary learning,Recognition system,Pattern recognition,Neural coding,Computer science,Feature extraction,Sign language,Artificial intelligence,RGB color model,Discriminative model
Conference
Citations 
PageRank 
References 
3
0.41
9
Authors
5
Name
Order
Citations
PageRank
Yongjun Jiang130.41
Jinxu Tao2101.60
Weiquan Ye330.41
Wu Wang430.41
Zhongfu Ye537949.33