Improved linear discrimination using time-frequency dictionaries
- 1 September 1995
- proceedings article
- Published by SPIE-Intl Soc Optical Eng
- p. 540-551
- https://doi.org/10.1117/12.217608
Abstract
We consider linear discriminant analysis in the setting where the objects (signals/images) have many dimensions (samples/pixels) and there are relatively few training samples. We discuss ways that time frequency dictionaries can be used to adaptively select a small set of derived features which lead to improved misclassification rates.Keywords
This publication has 0 references indexed in Scilit: