NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Collections About News Help Login
Back to Results
Computer classification of remotely sensed multispectral image data by extraction and classification of homogeneous objectsA method of classification of digitized multispectral images is developed and experimentally evaluated on actual earth resources data collected by aircraft and satellite. The method is designed to exploit the characteristic dependence between adjacent states of nature that is neglected by the more conventional simple-symmetric decision rule. Thus contextual information is incorporated into the classification scheme. The principle reason for doing this is to improve the accuracy of the classification. For general types of dependence this would generally require more computation per resolution element than the simple-symmetric classifier. But when the dependence occurs in the form of redundance, the elements can be classified collectively, in groups, therby reducing the number of classifications required.
Document ID
19760014577
Acquisition Source
Legacy CDMS
Document Type
Contractor Report (CR)
Authors
Kettig, R. L. (Purdue Univ. West Lafayette, IN, United States)
Date Acquired
September 3, 2013
Publication Date
January 1, 1975
Subject Category
Earth Resources And Remote Sensing
Report/Patent Number
LARS-IN-050975
NASA-CR-147403
Accession Number
76N21665
Funding Number(s)
CONTRACT_GRANT: NAS9-14016
Distribution Limits
Public
Copyright
Work of the US Gov. Public Use Permitted.

Related Records

There are no records associated with this record.
No Preview Available