Shift- and rotation-invariant interpattern heteroassociation (IHA) model

A shift- and rotation-invariant netral work using an interpattern heteroassociation (IHA) model is illustrated. The shift- and rotation-invariant properties are achived by using a set of binarized-encoded circular harmonic expansion (CHE) functions in the Fourier domain as the network training set. Because of the shift-invariant and symmetric properties of the modulus of Fourier spectrum, the problem of locating the center of the CHE functions can be avoided. Computer simulations and experimental demonstrations that demonstrate the shift- and the rotation-invariant properties of the proposed IHA neural net are provided.