skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

On Means and Their Asymptotics: Circles and Shape Spaces

Journal of mathematical imaging and vision, 2014-09, Vol.50 (1-2), p.98-106 [Peer Reviewed Journal]

Springer Science+Business Media New York 2013 ;ISSN: 0924-9907 ;EISSN: 1573-7683 ;DOI: 10.1007/s10851-013-0462-3

Full text available

Citations Cited by
  • Title:
    On Means and Their Asymptotics: Circles and Shape Spaces
  • Author: Huckemann, Stephan ; Hotz, Thomas
  • Subjects: Applications of Mathematics ; Computer Science ; Image Processing and Computer Vision ; Mathematical Methods in Physics ; Signal,Image and Speech Processing
  • Is Part Of: Journal of mathematical imaging and vision, 2014-09, Vol.50 (1-2), p.98-106
  • Description: We survey some effects that singular strata may have in the positive curvature context of circles and shape spaces when conducting (semi-)intrinsic statistical analyses. Here, the analysis of data on a stratified space is based on statistical descriptors defined in a possibly different stratified space. E.g. in geodesic principal component analysis for shape spaces, shape data are described by generalized geodesics which naturally form a shape space of their own, different from the original one. In a general context, if the descriptors are obtained as generalized Fréchet means, under rather general circumstances, a strong law of large numbers is valid. If furthermore the descriptors are sufficiently well behaved, a classical central limit theorem can be adopted. One of the crucial conditions is that hitting of singular strata as well as of cut loci, if present, must be controlled. We review the statistical role of the cut locus of intrinsic means for circles as well as that of singular strata for shape spaces (occurring where the group action is degenerate) and conclude with an identification of potential research directions.
  • Publisher: Boston: Springer US
  • Language: English
  • Identifier: ISSN: 0924-9907
    EISSN: 1573-7683
    DOI: 10.1007/s10851-013-0462-3
  • Source: Alma/SFX Local Collection
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait