Title :
Pattern recognition with invariance to similarity transformations based on the third-order correlation
Author_Institution :
Res. Sch. of Biol. Sci., Australian Nat. Univ., Canberra, ACT, Australia
Abstract :
Invariance to similarity transformations (simultaneous shift, rotation and scaling invariance) of images based on the third-order correlation was tested on accuracy to numerical errors and on robustness to additive noise. The invariance was then applied to the estimation of the rotation angles of images
Keywords :
correlation methods; fast Fourier transforms; image classification; image reconstruction; invariance; least mean squares methods; noise; pattern recognition; additive noise; numerical errors; pattern recognition; rotation angles; rotation invariance; scaling invariance; shift invariance; similarity transformations; third-order correlation; Additive white noise; Biology; Fourier transforms; Gaussian noise; Image retrieval; Information retrieval; Noise figure; Noise robustness; Pattern recognition; Testing;
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.1996.546817
