Application of the Karhunen-Loeve Expansion to Feature Extraction and Classification,
Abstract
The Karhunen-Loeve expansion has been used previously to extract important features for representing samples taken from a given distribution. A method is developed herein to use the Karhunen-Loeve expansion to extract features relevant to classification of a sample taken from one of two pattern classes. Numerical examples are presented to illustrate the technique. Also, it is shown that the properties of the proposed technique can be applied into two classes without a priori knowledge of the class. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 1969
- Accession Number
- AD0756265
Entities
People
- K. Fukunaga
- W. L. G. Koontz
Organizations
- Purdue University