A heteroscedastic extension of LDA based on multi-class matusita affinity

Mohammad Shahin Mahanta, Konstantinos N. PlataniotisICASSP 2012 · OpenReview

Abstract

Linear discriminant analysis (LDA), a conventional feature extraction technique, is a homoscedastic solution and ignores the second order information of the data. A heteroscedastic extension of LDA has been previously proposed which relies on the average pairwise Chernoff distances of the classes. However, in a multi-class scenario with number of classesC >; 2, the average of pairwise distances is not directly related to the classification error rate. Furthermore, the corresponding method imposes a high computational complexity of order O(C(C - 1)). This paper proposes an inherently multi-class heteroscedastic extension of LDA based on Matusita's separability measure, a multi-class generalization of the Chernoff distance which is related to multi-class error bounds. The proposed feature extractor can be trained non-iteratively with computational complexity of O(C). Experimental comparisons with the Chernoffmethod demonstrate both a performance improvement when estimated parameters are used, and a reduction of factor C - 1 in the computational load as predicted.
BibTeX
@inproceedings{mahanta2012heteroscedastic,
  author = {Mohammad Shahin Mahanta and Konstantinos N. Plataniotis},
  title = {{A heteroscedastic extension of LDA based on multi-class matusita affinity}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2012},
  url = {https://openreview.net/forum?id=A2oBRobgGe},
}

Loading related content...

Figure