Share Email Print

Proceedings Paper

Optimal Linear Discriminant Functions
Author(s): Vinod Sharma; David Casasent; D. Fetterly
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

A new class of discriminant filter functions for use in a matched filter correlator for multi-class distortion-invariant pattern recognition is described. Three variations of these optimal linear discriminant functions (OLDFs) that optimize different performance measures are described and initial performance results are presented.

Paper Details

Date Published: 21 January 1985
PDF: 6 pages
Proc. SPIE 0519, Analog Optical Processing and Computing, (21 January 1985); doi: 10.1117/12.945201
Show Author Affiliations
Vinod Sharma, Carnegie-Mellon University (United States)
Northeastern University (United States)
David Casasent, Carnegie-Mellon University (United States)
D. Fetterly, General Dynamics (United States)

Published in SPIE Proceedings Vol. 0519:
Analog Optical Processing and Computing
H. John Caulfield, Editor(s)

© SPIE. Terms of Use
Back to Top