Dictionary-based optical filter selection for multi-application spectral signature classification

Jun Ke, Kathrin Berkner, M. Dirk Robinson, David G. Stork

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We describe a method for selecting filter sets for simultaneously optimizing the classification rates in two separate spectral signature classification problems. Our system's performance is comparable to traditional hyper-or multispectral classifiers, but uses fewer filters.

Original languageEnglish
Title of host publicationDigital Image Processing and Analysis, DIPA 2010
Publication statusPublished - 2010
Externally publishedYes
EventDigital Image Processing and Analysis, DIPA 2010 - Tucson, AZ, United States
Duration: 7 Jun 20108 Jun 2010

Publication series

NameOptics InfoBase Conference Papers
ISSN (Electronic)2162-2701

Conference

ConferenceDigital Image Processing and Analysis, DIPA 2010
Country/TerritoryUnited States
CityTucson, AZ
Period7/06/108/06/10

Fingerprint

Dive into the research topics of 'Dictionary-based optical filter selection for multi-application spectral signature classification'. Together they form a unique fingerprint.

Cite this