Fisher Vector Coding for Covariance Matrix Descriptors Based on the Log-Euclidean and Affine Invariant Riemannian Metrics

Fisher Vector Coding for Covariance Matrix Descriptors Based on the Log-Euclidean and Affine Invariant Riemannian Metrics

This paper presents an overview of coding methods used to encode a set of covariance matrices. Starting from a Gaussian mixture model (GMM) adapted to the Log-Euclidean (LE) or affine invariant Riemannian metric, we propose a Fisher Vector (FV) descriptor adapted to each of these metrics: the Log-Eu...

Full description

Bibliographic Details
Main Authors: Ioana Ilea, Lionel Bombrun, Salem Said, Yannick Berthoumieu
Format: Article
Language:English
Published: MDPI AG 2018-06-01
Series:Journal of Imaging
Subjects:
bag of words
vector of locally aggregated descriptors
Fisher vector
log-Euclidean metric
affine invariant Riemannian metric
covariance matrix
Online Access:http://www.mdpi.com/2313-433X/4/7/85

Internet

http://www.mdpi.com/2313-433X/4/7/85

Similar Items