engleski

Supervised feature extraction for tensor objects based on maximization of mutual information

Several supervised feature extraction methods for tensor objects have been proposed recently, with applications in recognition of objects, faces and handwritten digits. However, the existing methods usually use only second order statistics of the data, typically through calculation of the within- and between-class scatters. Here we propose a method for supervised feature extraction for tensor objects based on maximization of an approximation of mutual information. In this way we utilize information contained in the higher order statistics of the data. Several experiments show that the proposed method results in highly discriminative features.

dimensionality reduction; tensor decomposition; feature extraction; mutual information

nije evidentirano