On the generalization of the mahalanobis distance Articles uri icon

publication date

  • January 2013

start page

  • 125

end page

  • 132

volume

  • 8258

international standard serial number (ISSN)

  • 0302-9743

electronic international standard serial number (EISSN)

  • 1611-3349

abstract

  • The Mahalanobis distance (MD) is a widely used measure in Statistics and Pattern Recognition. Interestingly, assuming that the data are generated from a Gaussian distribution, it considers the covariance matrix to evaluate the distance between a data point and the distribution mean. In this work, we generalize MD for distributions in the exponential family, providing both, a definition in terms of the data density function and a computable version. We show its performance on several artificial and real data scenarios.