Exploring generalized shape analysis by topological representations

doi:10.1016/j.patrec.2016.04.002

CASIA OpenIR > 智能感知与计算研究中心

	Exploring generalized shape analysis by topological representations
	Zhou, Zhen; Huang, Yongzhen; Wang, Liang; Tan, Tieniu
发表期刊	PATTERN RECOGNITION LETTERS
	2017-02-01
卷号	87 期号:87 页码:177-185
文章类型	Article
摘要	One of the most common properties of various data in pattern recognition is the shape, and the shape matters. However, the shape can appear with uncertain appearances, e.g., the shapes of a person in different poses. We realize that the most fundamental feature of any shape is the number of connected components, the number of holes and its higher dimensional counterparts. These are what we call topological invariants. This is the place where topology comes into play for pattern recognition. Persistent homology, one of the most powerful tools in algebraic topology, is proposed to compute these topological invariants at different resolutions. The proposed method, by firstly transferring the given data into a topological graph representation, i.e., the simplicial complex, can assemble discrete points into a global structure. Then by integrating with multiple filtrations and metric learning, both the global structure and different local parts can be taken into account at the same time. We test the proposed method in 21) shape classification, 2.5D gait identification and 3D facial expression recognition. Experimental results demonstrate the effectiveness of this generalized shape analysis method and show its potentials in different applications. Moreover, we provide a new insight for the generalized shape analysis. (C) 2016 Elsevier B.V. All rights reserved.
关键词	Topology Persistent Homology Shape Analysis Gait Recognition 3d Facial Expression Recognition
WOS标题词	Science & Technology ; Technology
DOI	10.1016/j.patrec.2016.04.002
关键词[WOS]	PERSISTENT HOMOLOGY ; GAIT RECOGNITION ; CLASSIFICATION
收录类别	SCI ; ISTP
语种	英语
项目资助者	National Basic Research Program of China(2012C6316300) ; National Natural Science Foundation of China(61135002) ; State Key Laboratory of Mathematical Engineering and Advanced Computing(2015A06)
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000395616700022
引用统计	被引频次：6[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/14428
专题	智能感知与计算研究中心
作者单位	Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Ctr Res Intelligent Percept & Comp, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Zhou, Zhen,Huang, Yongzhen,Wang, Liang,et al. Exploring generalized shape analysis by topological representations[J]. PATTERN RECOGNITION LETTERS,2017,87(87):177-185.
APA	Zhou, Zhen,Huang, Yongzhen,Wang, Liang,&Tan, Tieniu.(2017).Exploring generalized shape analysis by topological representations.PATTERN RECOGNITION LETTERS,87(87),177-185.
MLA	Zhou, Zhen,et al."Exploring generalized shape analysis by topological representations".PATTERN RECOGNITION LETTERS 87.87(2017):177-185.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
论文 Exploring General（2603KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载