Title :
Adaptive invariant novelty filters
Author :
Szu, Harold H. ; Messner, Richard A.
Author_Institution :
Naval Research Laboratory, Washington, DC, USA
fDate :
3/1/1986 12:00:00 AM
Abstract :
The multiple-channel novelty filters of associative memory are derived from the retina neuron network point-spread function. Scale and rotation invariance is achieved by the input data flowing through the nonuniform polar exponential sampling to a uniform output space. Image domain bandpassing techniques are then used to extract the low-band and high-band frequency contents of the equivalent novelty filters.
Keywords :
Adaptive filters; Associative memory; Data mining; Frequency; Humans; Image sampling; Neurons; Nonlinear filters; Retina; Visual system;
Journal_Title :
Proceedings of the IEEE
DOI :
10.1109/PROC.1986.13494