Analysis of Multilinear Subspaces Based on Geodesic Distance

Tensor principal component analysis enables the efficient analysis of spatial textures of volumetric images and spatio-temporal changes of volumetric video sequences. To extend the subspace methods for analysis of linear subspaces, we are required to quantitatively evaluate the differences between m...

Full description

Saved in:
Bibliographic Details
Published inComputer Analysis of Images and Patterns Vol. 10424; pp. 384 - 396
Main Authors Itoh, Hayato, Imiya, Atsushi, Sakai, Tomoya
Format Book Chapter
LanguageEnglish
Published Switzerland Springer International Publishing AG 2017
Springer International Publishing
SeriesLecture Notes in Computer Science
Online AccessGet full text

Cover

More Information
Summary:Tensor principal component analysis enables the efficient analysis of spatial textures of volumetric images and spatio-temporal changes of volumetric video sequences. To extend the subspace methods for analysis of linear subspaces, we are required to quantitatively evaluate the differences between multilinear subspaces. This discrimination of multilinear subspaces is achieved by computing the geodesic distance between tensor subspaces.
ISBN:3319646885
9783319646886
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-319-64689-3_31