Implementation of an advanced table look-up classifier for large area land-use classificationSoftware employing Eppler's improved table look-up approach to pattern recognition has been developed, and results from this software are presented. The look-up table for each class is a computer representation of a hyperellipsoid in four dimensional space. During implementation of the software Eppler's look-up procedure was modified to include multiple ranges in order to accommodate hollow regions in the ellipsoids. In a typical ERTS classification run less than 6000 36-bit computer words were required to store tables for 24 classes. Classification results from the improved table look-up are identical with those produced by the conventional method, i.e., by calculation of the maximum likelihood decision rule at the moment of classification. With the new look-up approach an entire ERTS MSS frame can be classified into 24 classes in 1.3 hours, compared to 22.5 hours required by the conventional method. The new software is coded completely in FORTRAN to facilitate transfer to other digital computers.
Document ID
19750033081
Acquisition Source
Legacy CDMS
Document Type
Conference Proceedings
Authors
Jones, C. (NASA Johnson Space Center Earth Resources Laboratory, Bay St. Louis, Miss., United States)
Date Acquired
August 8, 2013
Publication Date
January 1, 1974
Subject Category
Earth Resources And Remote Sensing
Meeting Information
Meeting: International Symposium on Remote Sensing of Environment