USE OF SELF ORGANIZED MAPS FOR FEATURE EXTRACTION OF HYPERSPECTRAL DATA

منو

" USE OF SELF ORGANIZED MAPS FOR FEATURE EXTRACTION OF HYPERSPECTRAL DATA "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	151246
Doc. No	:	ET23038
Main Entry	:	Thomas Calvin Null III
Title Proper	:	USE OF SELF ORGANIZED MAPS FOR FEATURE EXTRACTION OF HYPERSPECTRAL DATA
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	In this paper, the problem of analyzing hyperspecbal data is presented. Thecomplex@ of multi-dimensional data Ieads to the need for computer assisted datacompression and labeling of important features. A brief overview of Self-OrganizingMaps and their variants is given and then two possible methods of data analysis areexamined. These methods are incorporated into a program derived fromsom-toolbod. In this p r o m ASD data (data collected by an Analytical SpectralDevice sensor) is read into a variable, relevant bands for discrimhation betweenclasses are extracted, and several different-....,....-...,..tested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject	:	Electericl tess
	:	برق
electronic file name	:	TL46270.pdf
Title and statement of responsibility and	:	USE OF SELF ORGANIZED MAPS FOR FEATURE EXTRACTION OF HYPERSPECTRAL DATA [Thesis]