NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Collections About News Help Login
Back to Results
Fuzzy set methods for object recognition in space applicationsProgress on the following tasks is reported: feature calculation; membership calculation; clustering methods (including initial experiments on pose estimation); and acquisition of images (including camera calibration information for digitization of model). The report consists of 'stand alone' sections, describing the activities in each task. We would like to highlight the fact that during this quarter, we believe that we have made a major breakthrough in the area of fuzzy clustering. We have discovered a method to remove the probabilistic constraints that the sum of the memberships across all classes must add up to 1 (as in the fuzzy c-means). A paper, describing this approach, is included.
Document ID
19920023849
Acquisition Source
Legacy CDMS
Document Type
Contractor Report (CR)
Authors
Keller, James M. (Missouri Univ. Columbia., United States)
Date Acquired
September 6, 2013
Publication Date
March 31, 1992
Subject Category
Computer Programming And Software
Report/Patent Number
NAS 1.26:190388
NASA-CR-190388
Accession Number
92N33093
Funding Number(s)
PROJECT: RICIS PROJ. SE-42
CONTRACT_GRANT: NCC9-16
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