• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Wang, Boyue (Wang, Boyue.) | Hu, Yongli (Hu, Yongli.) (Scholars:胡永利) | Gao, Junbin (Gao, Junbin.) | Ali, Muhammad (Ali, Muhammad.) | Tien, David (Tien, David.) | Sun, Yanfeng (Sun, Yanfeng.) (Scholars:孙艳丰) | Yin, Baocai (Yin, Baocai.) (Scholars:尹宝才)

Indexed by:

EI Scopus SCIE

Abstract:

Symmetric Positive semi-Definite (SPD) matrices, as a kind of effective feature descriptors, have been widely used in pattern recognition and computer vision tasks. Affine-invariant metric (AIM) is a popular way to measure the distance between SPD matrices, but it imposes a high computational burden in practice. Compared with AIM, the Log-Euclidean metric embeds the SPD manifold via the matrix logarithm into a Euclidean space in which only classical Euclidean computation is involved. The advantage of using this metric for the non-linear SPD matrices representation of data has been recognized in some domains such as compressed sensing, however one pays little attention to this metric in data clustering. In this paper, we propose a novel Low Rank Representation (LRR) model on SPD matrices space with Log-Euclidean metric (LogELRR), which enables us to handle non-linear data through a linear manipulation manner. To further explore the intrinsic geometry distance between SPD matrices, we embed the SPD matrices into Reproductive Kernel Hilbert Space (RKHS) to form a family of kernels on SPD matrices based on the Log-Euclidean metric and construct a novel kernelized LogELRR method. The clustering results on a wide range of datasets, including object images, facial images, 3D objects, texture images and medical images, show that our proposed methods overcome other conventional clustering methods. (C) 2017 Published by Elsevier Ltd.

Keyword:

Symmetrical positive definite matrices Log-Euclidean metric Subspace clustering Low Rank Representation

Author Community:

  • [ 1 ] [Hu, Yongli]Beijing Adv Innovat Ctr Future Internet Technol, Beijing 100124, Peoples R China
  • [ 2 ] [Sun, Yanfeng]Beijing Adv Innovat Ctr Future Internet Technol, Beijing 100124, Peoples R China
  • [ 3 ] [Yin, Baocai]Beijing Adv Innovat Ctr Future Internet Technol, Beijing 100124, Peoples R China
  • [ 4 ] [Wang, Boyue]Beijing Univ Technol, Coll Metropolitan Transportat, Beijing Municipal Key Lab Multimedia & Intelligen, Beijing 100124, Peoples R China
  • [ 5 ] [Hu, Yongli]Beijing Univ Technol, Coll Metropolitan Transportat, Beijing Municipal Key Lab Multimedia & Intelligen, Beijing 100124, Peoples R China
  • [ 6 ] [Sun, Yanfeng]Beijing Univ Technol, Coll Metropolitan Transportat, Beijing Municipal Key Lab Multimedia & Intelligen, Beijing 100124, Peoples R China
  • [ 7 ] [Yin, Baocai]Beijing Univ Technol, Coll Metropolitan Transportat, Beijing Municipal Key Lab Multimedia & Intelligen, Beijing 100124, Peoples R China
  • [ 8 ] [Gao, Junbin]Univ Sydney, Business Sch, Discipline Business Analyt, Sydney, NSW 2006, Australia
  • [ 9 ] [Wang, Boyue]Charles Sturt Univ, Sch Comp & Math, Bathurst, NSW 2795, Australia
  • [ 10 ] [Ali, Muhammad]Charles Sturt Univ, Sch Comp & Math, Bathurst, NSW 2795, Australia
  • [ 11 ] [Tien, David]Charles Sturt Univ, Sch Comp & Math, Bathurst, NSW 2795, Australia
  • [ 12 ] [Yin, Baocai]Dalian Univ Technol, Coll Comp Sci & Technol, Fac Elect Informat & Elect Engn, Dalian 116620, Peoples R China

Reprint Author's Address:

  • 胡永利

    [Hu, Yongli]Beijing Adv Innovat Ctr Future Internet Technol, Beijing 100124, Peoples R China;;[Hu, Yongli]Beijing Univ Technol, Coll Metropolitan Transportat, Beijing Municipal Key Lab Multimedia & Intelligen, Beijing 100124, Peoples R China

Show more details

Related Keywords:

Related Article:

Source :

PATTERN RECOGNITION

ISSN: 0031-3203

Year: 2018

Volume: 76

Page: 623-634

8 . 0 0 0

JCR@2022

ESI Discipline: ENGINEERING;

ESI HC Threshold:156

JCR Journal Grade:1

Cited Count:

WoS CC Cited Count: 16

SCOPUS Cited Count: 18

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 1

Online/Total:781/5309110
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.