The Matusita measure between two probability distributions and
is given by:
where describe the whole space again. The term
is called the Bhattacharyya measure [1]. In our case the distance becomes:
Thus:
Unlike the Kullback-Leibler divergence, the Bhattacharyya term is symmetric and is invariant to scale in the case of two Gaussian probability density distributions. The Matusita measure inherits these properties.