Skip to Main content Skip to Navigation
Conference papers

A New Closed-Form Information Metric for Shape Analysis

Abstract : Recently, a unifying framework was introduced for shape matching that uses mixture-models and the Fisher-Rao metric to couple both the shape representation and deformation. A fundamental drawback of the Fisher-Rao metric is that it is NOT available in closed-form for the mixture models making shape comparisons computationally very expensive. Here, we propose a new Riemannian metric based on generalized Á- entropy measures. In sharp contrast to the Fisher-Rao metric, our new metric is available in closed-form.
Document type :
Conference papers
Complete list of metadata

Cited literature [3 references]  Display  Hide  Download

https://hal.inria.fr/inria-00635898
Contributor : Service Ist Inria Sophia Antipolis-Méditerranée / I3s Connect in order to contact the contributor
Submitted on : Wednesday, October 26, 2011 - 11:38:16 AM
Last modification on : Friday, May 21, 2021 - 7:30:02 PM
Long-term archiving on: : Sunday, December 4, 2016 - 3:50:03 PM

File

Peter_MFCA06.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00635898, version 1

Collections

Citation

Adrian Peter, Anand Rangarajan. A New Closed-Form Information Metric for Shape Analysis. 1st MICCAI Workshop on Mathematical Foundations of Computational Anatomy: Geometrical, Statistical and Registration Methods for Modeling Biological Shape Variability, Oct 2006, Copenhagen, Denmark. pp.100-101. ⟨inria-00635898⟩

Share

Metrics

Record views

32

Files downloads

141