Abstract :
The Karhunen-Lo6ve 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.
Keywords :
Clustering, feature extraction, feature selection, Karhunen-Loeve expansion, pattern recognition, unsupervised learning.; Autocorrelation; Character recognition; Clustering algorithms; Covariance matrix; Feature extraction; Integral equations; Pattern recognition; Random processes; Time measurement; Unsupervised learning; Clustering, feature extraction, feature selection, Karhunen-Loeve expansion, pattern recognition, unsupervised learning.;
