DocumentCode :
1639934
Title :
Multiple geometrical filters for 3D scale-invariant image representation of planar objects
Author :
Murino, Vittorio ; Rebollini, Stefano ; Foresti, Gianluca ; Regazzoni, Carlo S.
Author_Institution :
Dept. of Biophys. & Electron. Eng., Genoa Univ., Italy
fYear :
1992
Firstpage :
531
Lastpage :
534
Abstract :
A low-level approach for 3-D invariant recognition of planar object from a centered monocular view is presented. The proposed scheme uses a distributed bank of filters that perform geometrical mapping on spatial image domain to generate a multidimensional (4-D) description. This image representation achieves invariance to 2-D rotation, scaling and perspective projection. Invariant classification and pose estimation, in terms of slant and tilt of the planar object, are obtained by direct matching between the representation and an undistorted reference model
Keywords :
filtering and prediction theory; image processing; image recognition; 2D rotation invariance; 3D scale-invariant image representation; centered monocular view; filter bank; geometrical mapping; invariant classification; multiple geometrical filters; object recognition; perspective projection invariance; planar objects; pose estimation; scaling invariance; slant; spatial image domain; tilt; undistorted reference model; Conformal mapping; Filter bank; Fourier transforms; Frequency; Image recognition; Image representation; Multidimensional systems; Noise shaping; Object recognition; Visual system;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Time-Frequency and Time-Scale Analysis, 1992., Proceedings of the IEEE-SP International Symposium
Conference_Location :
Victoria, BC
Print_ISBN :
0-7803-0805-0
Type :
conf
DOI :
10.1109/TFTSA.1992.274143
Filename :
274143
Link To Document :
بازگشت