File Exchange

image thumbnail

Unscented Hellinger distance between GMMs

version 1.2 (26.4 KB) by

The code calculates a metric between a pair of multivariate Gaussian Mixture Models.

8 Downloads

Updated

View License

This is a demo code for the unscented Hellinger distance between a pair of Gaussian mixture models. The code follows the derivation of the multivariate unscented Hellinger distance introduced in [1]. Unlike the Kullback-Leibler divergence, the Hellinger distance is a proper metric between the distributions and is constrained to interval (0,1) with 0 meaning complete similarity and 1 complete dissimilarity.

[1] M. Kristan, A. Leonardis, D. Skočaj, "Multivariate online Kernel Density Estimation", Pattern Recognition, 2011. (url: http://vicos.fri.uni-lj.si/data/publications/KristanPR11.pdf)

Comments and Ratings (0)

Updates

1.2

There was an error in the visualization part. The visualization "/drawTools/"

MATLAB Release
MATLAB 7.12 (R2011a)

Download apps, toolboxes, and other File Exchange content using Add-On Explorer in MATLAB.

» Watch video