Novel projection pursuit indices for feature extraction and classification: An inter-comparison in a remote sensing application

Author

Bachmann, Charles M.

Author_Institution

Div. of Remote Sensing, Naval Res. Lab., Washington, DC, USA

fYear

1997

fDate

24-26 Sep 1997

Firstpage

54

Lastpage

63

Abstract

Projection pursuit (PP) techniques are used to search for statistically interesting low-dimensional projections of complex, high-dimensional data. These projections reveal data structure useful for automatic classification applications. We derive a novel class of PP algorithms, comparing them with known PP algorithms. Texture-based cloud detection in airborne visible/infrared imaging spectrometer (AVIRIS) imagery from the Jet Propulsion Laboratory is provided as a basis for inter-comparison

Keywords

clouds; data structures; feature extraction; image classification; neural nets; remote sensing; AVIRIS imagery; airborne visible/infrared imaging spectrometer imagery; classification; complex high-dimensional data; feature extraction; neural nets; projection pursuit indices; remote sensing application; statistically interesting low-dimensional projections; texture-based cloud detection; Cost function; Data structures; Feature extraction; High performance computing; Hydrodynamics; Laboratories; Particle measurements; Principal component analysis; Pursuit algorithms; Remote sensing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks for Signal Processing [1997] VII. Proceedings of the 1997 IEEE Workshop

Conference_Location

Amelia Island, FL

ISSN

1089-3555

Print_ISBN

0-7803-4256-9

Type

conf

DOI

10.1109/NNSP.1997.622383

Filename

622383