A nonlinear distance metric criterion for feature selection in the measurement space

https://doi.org/10.1016/0020-0255(75)90032-8Get rights and content

Abstract

In this paper a nonlinear distance metric criterion for feature selection in the measurement space is proposed. The criterion is not only a more reliable measure of class separability than criteria based on the Euclidean distance metric but also computationally more efficient.

References (5)

  • J. Kittler

    Mathematical methods of feature selection in pattern recognition

  • M. Michael et al.

    Experimental study of information measure and inter-class distance ratios on feature selection and ordering

    IEEE Trans.

    (1973)
There are more references available in the full text version of this article.

Cited by (0)

Present address: Electronics Department, Southampton University, Southampton SO9 5NH, Hampshire, England.

View full text