Title :
Feature Extraction Using Problem Localization
Author :
Short, Robert D. ; Fukunaga, Keinosuke
Author_Institution :
Sperry Research Center, Sudbury, MA 01776.
fDate :
5/1/1982 12:00:00 AM
Abstract :
Feature extraction is considered as a mean-quare estimation of the Bayes risk vector. The problem is simplified by partitioning the distribution space into local subregions and performing a linear estimation in each subregion. A modified clustering algorithm is used to fimd the partitioning which minimizes the mean-square error.
Keywords :
Artificial intelligence; Clustering algorithms; Cost function; Feature extraction; Nearest neighbor searches; Partitioning algorithms; Pattern recognition; Piecewise linear techniques; Vectors; Bayes risk; classification; feature extraction; piecewise linear features; problem localization;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.1982.4767252
