NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Multiscale vector fields for image pattern recognitionA uniform processing framework for low-level vision computing in which a bank of spatial filters maps the image intensity structure at each pixel into an abstract feature space is proposed. Some properties of the filters and the feature space are described. Local orientation is measured by a vector sum in the feature space as follows: each filter's preferred orientation along with the strength of the filter's output determine the orientation and the length of a vector in the feature space; the vectors for all filters are summed to yield a resultant vector for a particular pixel and scale. The orientation of the resultant vector indicates the local orientation, and the magnitude of the vector indicates the strength of the local orientation preference. Limitations of the vector sum method are discussed. Investigations show that the processing framework provides a useful, redundant representation of image structure across orientation and scale.
Document ID
19910034881
Acquisition Source
Legacy CDMS
Document Type
Conference Paper
Authors
Low, Kah-Chan
(North Carolina, University Chapel Hill, United States)
Coggins, James M.
(NASA Goddard Space Flight Center Greenbelt, MD; North Carolina, University, Chapel Hill, United States)
Date Acquired
August 15, 2013
Publication Date
January 1, 1990
Subject Category
Cybernetics
Meeting Information
Meeting: Intelligent Robots and Computer Vision VIII: Algorithms and Techniques
Location: Philadelphia, PA
Country: United States
Start Date: November 6, 1989
End Date: November 10, 1989
Accession Number
91A19504
Distribution Limits
Public
Copyright
Other

Available Downloads

There are no available downloads for this record.
No Preview Available