Jensen-Bregman LogDet divergence with application to efficient similarity search for covariance matrices

Anoop Cherian, Suvrit Sra, Arindam Banerjee, Nikolaos Papanikolopoulos

Research output: Contribution to journalArticlepeer-review

Abstract

Covariance matrices have found success in several computer vision applications, including activity recognition, visual surveillance, and diffusion tensor imaging. This is because they provide an easy platform for fusing multiple features compactly. An important task in all of these applications is to compare two covariance matrices using a (dis)similarity function, for which the common choice is the Riemannian metric on the manifold inhabited by these matrices. As this Riemannian manifold is not flat, the dissimilarities should take into account the curvature of the manifold. As a result, such distance computations tend to slow down, especially when the matrix dimensions are large or gradients are required. Further, suitability of the metric to enable efficient nearest neighbor retrieval is an important requirement in the contemporary times of big data analytics. To alleviate these difficulties, this paper proposes a novel dissimilarity measure for covariances, the Jensen-Bregman LogDet Divergence (JBLD). This divergence enjoys several desirable theoretical properties and at the same time is computationally less demanding (compared to standard measures). Utilizing the fact that the square root of JBLD is a metric, we address the problem of efficient nearest neighbor retrieval on large covariance datasets via a metric tree data structure. To this end, we propose a K-Means clustering algorithm on JBLD. We demonstrate the superior performance of JBLD on covariance datasets from several computer vision applications.

Original languageEnglish (US)
Article number6378374
Pages (from-to)2161-2174
Number of pages14
JournalIEEE transactions on pattern analysis and machine intelligence
Volume35
Issue number9
DOIs
StatePublished - 2013
Externally publishedYes

Keywords

  • activity recognition
  • Bregman divergence
  • image search
  • LogDet divergence
  • nearest neighbor search
  • Region covariance descriptors
  • video surveillance

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Jensen-Bregman LogDet divergence with application to efficient similarity search for covariance matrices'. Together they form a unique fingerprint.

Cite this