Multiscale covariance fields, local scales, and shape transforms

Date

2013

Authors

Martinez, Diego H. Diaz
Memoli, Facundo
Mio, Washington

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

Lecture Notes in Computer Science, 2013 / F. Nielsen, F. Barbaresco (eds.), pp.794-801

Statement of Responsibility

Diego H. Diaz Martinez, Facundo Mémoli, and Washington Mio

Conference Name

International SEE Conference on Geometric Science of Information (1st : 2013 : Paris)

Abstract

We introduce the notion of multiscale covariance tensor fields associated with a probability measure on Euclidean space and use these fields to define local scales at a point and to construct shape transforms. Local scales at x may be interpreted as scales at which key geometric features of the data organization around x are revealed. Shape transforms are employed to identify points that are most salient in terms of the local-global shape of a probability distribution, yielding a compact summary of the geometry of the distribution.

School/Discipline

School of Computer Science

Dissertation Note

Provenance

Description

Access Status

Rights

© Springer-Verlag Berlin Heidelberg 2013

License

Grant ID

Published Version

Call number

Persistent link to this record