DocumentCode :
1375989
Title :
Dominant-subspace invariants
Author :
Arnold, D.G. ; Sturtz, Kirk ; Velten, Vince ; Nandhakumar, N.
Author_Institution :
Wright-Patterson AFB, Air Force Res. Lab., Dayton, OH, USA
Volume :
22
Issue :
7
fYear :
2000
fDate :
7/1/2000 12:00:00 AM
Firstpage :
649
Lastpage :
662
Abstract :
Object recognition requires robust and stable features that are unique in feature space. Lie group analysis provides a constructive procedure to determine such features, called invariants, when they exist. Absolute invariants are rare in general, so quasi-invariants relax the restrictions required for absolute invariants and, potentially, can be just as useful in real-world applications. The paper develops the concept of a dominant-subspace invariant, a particular type of quasi-invariant, using the theory of Lie groups. A constructive algorithm is provided that fundamentally seeks to determine an integral submanifold which, in practice, is a good approximation to the orbit of the Lie group action. This idea is applied to the long-wave infrared problem and experimental results are obtained supporting the approach. Other application areas are cited
Keywords :
Lie groups; infrared imaging; invariance; object recognition; Lie group action; Lie group analysis; absolute invariants; constructive algorithm; dominant-subspace invariants; feature space; integral submanifold; long-wave infrared problem; quasi-invariants; Approximation algorithms; Force sensors; Intelligent sensors; Kirk field collapse effect; Lighting; Object recognition; Physics; Robustness; Sensor phenomena and characterization; Solid modeling;
fLanguage :
English
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publisher :
ieee
ISSN :
0162-8828
Type :
jour
DOI :
10.1109/34.865182
Filename :
865182
Link To Document :
بازگشت