1 September 1990 Sequential classification into m multivariate populations using the information based on small samples
Author Affiliations +
Proceedings Volume 1360, Visual Communications and Image Processing '90: Fifth in a Series; (1990) https://doi.org/10.1117/12.24144
Event: Visual Communications and Image Processing '90, 1990, Lausanne, Switzerland
Abstract
In this paper, the classification problem is considered when the alternative distributions have given functional forms but with unspecified parameters. No systematic attempt seems to have been made to offer solutions for small samples. Here a way for eliminating nuisance parameters from the classification problem is proposed, which is based on consideration of a statistic transforming the original observations, the transformation so chosen that the distribution of this statistic does not depend on the nuisance parameters. The price paid for the elimination of the nuisance parameters is the fact that instead of the original n observations we are left with n1 (n1
© (1990) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Nicholas A. Nechval, Nicholas A. Nechval, } "Sequential classification into m multivariate populations using the information based on small samples", Proc. SPIE 1360, Visual Communications and Image Processing '90: Fifth in a Series, (1 September 1990); doi: 10.1117/12.24144; https://doi.org/10.1117/12.24144
PROCEEDINGS
12 PAGES


SHARE
Back to Top