Sparse Observation (SO) Alignment for Sign Language Recognition

doi:10.1016/j.neucom.2015.10.112

	Sparse Observation (SO) Alignment for Sign Language Recognition
	Wang, Hanjie 1; Chai, Xiujuan 1,3; Chen, Xilin 1,2,3
	2016-01-29
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
卷号	175 页码:674-685
摘要	In this paper, we propose a method for robust Sign Language Recognition from RGB-D data. A Sparse Observation (SO) description is proposed to character each sign in terms of the typical hand postures. Concretely speaking, the SOs are generated by considering the typical posture fragments, where hand motions are relatively slow and hand shapes are stable. Thus the matching between two sign words is converted to measure the similarity computing between two aligned SO sequences. The alignment is formulated as a variation of Stable Marriage Problem (SMP). The classical "propose-engage" idea is extended to get the order preserving matched SO pairs. In the training stage, the multiple instances from one sign are fused to generate single SO template. In the recognition stage, SOs of each probe sign "propose" to SOs of the templates for the purpose of reasonable similarity computing. To further speed up the SO alignment, hand posture relationship map is constructed as a strong prior to generate the distinguished low-dimensional feature of SO. Moreover, to get much better performance, the motion trajectory feature is integrated. Experiments on two large datasets and an extra Chalearn Multi-modal Gesture Dataset demonstrate that our algorithm has much higher accuracy with only 1/10 time cost compared with the HMM and DTW based methods. (C) 2015 Elsevier B.V. All rights reserved.
关键词	Sign language Recognition Hidden Markov Model Dynamic Time Warping Stable Marriage Problem RGB-D data
DOI	10.1016/j.neucom.2015.10.112
收录类别	SCI
语种	英语
资助项目	Microsoft Research Asia ; Natural Science Foundation of China[61390511] ; Natural Science Foundation of China[61472398] ; FiDiPro program of Tekes
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000367756600065
出版者	ELSEVIER SCIENCE BV
引用统计	被引频次：20[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/8927
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Chai, Xiujuan
作者单位	1.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Oulu, Dept Comp Sci & Engn, SF-90100 Oulu, Finland 3.Cooperat Medianet Innovat Ctr, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Wang, Hanjie,Chai, Xiujuan,Chen, Xilin. Sparse Observation (SO) Alignment for Sign Language Recognition[J]. NEUROCOMPUTING,2016,175:674-685.
APA	Wang, Hanjie,Chai, Xiujuan,&Chen, Xilin.(2016).Sparse Observation (SO) Alignment for Sign Language Recognition.NEUROCOMPUTING,175,674-685.
MLA	Wang, Hanjie,et al."Sparse Observation (SO) Alignment for Sign Language Recognition".NEUROCOMPUTING 175(2016):674-685.