Title :
Weighted Parzen windows for pattern classification
Author :
Babich, Gregory A. ; Camps, Octavia I.
Author_Institution :
Appl. Res. Lab., Pennsylvania State Univ., University Park, PA, USA
fDate :
5/1/1996 12:00:00 AM
Abstract :
This paper introduces the weighted-Parzen-window classifier. The proposed technique uses a clustering procedure to find a set of reference vectors and weights which are used to approximate the Parzen-window (kernel-estimator) classifier. The weighted-Parzen-window classifier requires less computation and storage than the full Parzen-window classifier. Experimental results showed that significant savings could be achieved with only minimal, if any, error rate degradation for synthetic and real data sets
Keywords :
approximation theory; estimation theory; image classification; probability; Bayes error; clustering; discriminant analysis; error rate degradation; nonparametric classifiers; pattern classification; training samples; weighted Parzen windows; Degradation; Density functional theory; Entropy; Error analysis; Kernel; Monitoring; Pattern analysis; Pattern classification; Pattern recognition; Training data;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
