Title :
Set of invariant features for three-dimensional gray-level objects by harmonic analysis
Author :
Zribi, Mourad ; Fonga, Hubert ; Ghorbel, Faouzi
Author_Institution :
GRIF, Villeneuve d´´Ascq, France
Abstract :
The recognition of three-dimensional objects of various size, position and orientation, is an important and difficult problem in scene analysis. The description by moment invariants is recognized as the usual method in this case. Here, we intend to introduce another solution based on the harmonic analysis on a given group. Gray level three-dimensional objects are considered in this paper. Such a description is invariant with respect to general three-dimensional Euclidean motions. Stability under small shape distortions is proven experimentally in the case of superquadric volumes
Keywords :
Fourier transforms; group theory; harmonic analysis; image representation; image texture; object recognition; stereo image processing; 3D Euclidean motions; 3D gray-level object recognition; Fourier transform; group representation theory; harmonic analysis; image texture; invariant features; scene analysis; shape distortions; shape representation; Equations; Fourier transforms; Harmonic analysis; Image analysis; Image processing; Image recognition; Shape; Stability;
Conference_Titel :
Pattern Recognition, 1996., Proceedings of the 13th International Conference on
Conference_Location :
Vienna
Print_ISBN :
0-8186-7282-X
DOI :
10.1109/ICPR.1996.546086