Accession Number : ADA304274

Title :   Hyperspectral Imagery Analysis Using Neural Network Techniques.

Descriptive Note : Master's thesis,

Corporate Author : NAVAL POSTGRADUATE SCHOOL MONTEREY CA

Personal Author(s) : Gautreaux, Mark M.

PDF Url : ADA304274

Report Date : JUN 1995

Pagination or Media Count : 108

Abstract : Every material has a unique electromagnetic reflectance/emission signature which can be used to identify it. Hyperspectral imagers, by collecting high spectral resolution data, provide the ability to identify these spectral signatures. Utilization and exploitation of hyperspectral data is challenging because of the enormous data volume produced by these imagers. Most current processing and analyzation techniques involve dimensionality reduction, during which some information is lost. This thesis demonstrates the ability of neural networks and the Kohonen Self-Organizing Map to classify hyperspectral data. The possibility of real time processing is addressed. (AN)

Descriptors :   *IMAGE PROCESSING, *NEURAL NETS, DATA BASES, ALGORITHMS, FOURIER TRANSFORMATION, OPTIMIZATION, DATA MANAGEMENT, REAL TIME, CAMOUFLAGE, LEARNING MACHINES, THESES, OPTICAL DATA, OPTICAL IMAGES, HIGH RESOLUTION, CORRELATION, DATA REDUCTION, BACKGROUND, OPTICAL DETECTORS, PIXELS, REMOTE DETECTION, ERROR CORRECTION CODES, FOURIER SPECTROMETERS, ELECTROMAGNETIC SPECTRA, MICHELSON INTERFEROMETERS, IMAGE RESTORATION, SPECTRUM SIGNATURES, SELF ORGANIZING SYSTEMS.

Subject Categories : Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE