Accession Number : AD0756265

Title :   Application of the Karhunen-Loeve Expansion to Feature Extraction and Classification,

Corporate Author : PURDUE UNIV LAFAYETTE IND SCHOOL OF ELECTRICAL ENGINEERING

Personal Author(s) : Fukunaga,K. ; Koontz,W. L. G.

Report Date : SEP 1969

Pagination or Media Count : 35

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)

Descriptors :   (*PATTERN RECOGNITION, CLASSIFICATION), SAMPLING, MATRICES(MATHEMATICS), TRANSFORMATIONS(MATHEMATICS), ALGORITHMS

Subject Categories : Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE