NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Collections About News Help Login
Back to Results
Classifying multispectral data by neural networksSeveral energy functions for synthesizing neural networks are tested on 2-D synthetic data and on Landsat-4 Thematic Mapper data. These new energy functions, designed specifically for minimizing misclassification error, in some cases yield significant improvements in classification accuracy over the standard least mean squares energy function. In addition to operating on networks with one output unit per class, a new energy function is tested for binary encoded outputs, which result in smaller network sizes. The Thematic Mapper data (four bands were used) is classified on a single pixel basis, to provide a starting benchmark against which further improvements will be measured. Improvements are underway to make use of both subpixel and superpixel (i.e. contextual or neighborhood) information in tile processing. For single pixel classification, the best neural network result is 78.7 percent, compared with 71.7 percent for a classical nearest neighbor classifier. The 78.7 percent result also improves on several earlier neural network results on this data.
Document ID
19930016787
Acquisition Source
Legacy CDMS
Document Type
Conference Paper
Authors
Telfer, Brian A. (Naval Surface Warfare Center Silver Spring, MD., United States)
Szu, Harold H. (Naval Surface Warfare Center Silver Spring, MD., United States)
Kiang, Richard K. (NASA Goddard Space Flight Center Greenbelt, MD, United States)
Date Acquired
September 6, 2013
Publication Date
January 1, 1993
Publication Information
Publication: The 1993 Goddard Conference on Space Applications of Artificial Intelligence
Subject Category
Cybernetics
Accession Number
93N25976
Distribution Limits
Public
Copyright
Work of the US Gov. Public Use Permitted.

Related Records

IDRelationTitle19930016772Collected WorksThe 1993 Goddard Conference on Space Applications of Artificial Intelligence
No Preview Available