Use of rejection class to enhance airborne imagery classification

Author

Bennett, H.H., Jr. ; Campbell, R.L., Jr. ; Younan, N.H.

Author_Institution

R&D Center, US Army Corps of Eng., Vicksburg, MS, USA

Volume

2

fYear

1999

fDate

24-27 Oct. 1999

Firstpage

845

Abstract

The performance of a prior classification work is enhanced by introducing a rejection class that accurately describes a particular source of false alarm. Success of this enhancement is measured by observing changes in the receiver operating characteristic (ROC) curves corresponding to two different fixed strengths of the rejection class. Source data is taken from airborne imagery collected by a line-scanner system known as REMIDS (Remote Identification System) through funding from the Environmental Security Technology Certification Program (ESTCP).

Keywords

identification; image classification; image enhancement; military systems; REMIDS; ROC curves; Remote Identification System; airborne imagery classification; false alarm; line-scanner system; performance; receiver operating characteristic curves; rejection class; Certification; Data security; Electronic mail; Paints; Polarization; Reflectivity; Research and development; Telephony; Temperature; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems, and Computers, 1999. Conference Record of the Thirty-Third Asilomar Conference on

Conference_Location

Pacific Grove, CA, USA

ISSN

1058-6393

Print_ISBN

0-7803-5700-0

Type

conf

DOI

10.1109/ACSSC.1999.831829

Filename

831829