Department of Pattern Recognition

(eng): In this paper we proposed a method to design and numerically calculate high-orderrotation invariants from Gaussian–Hermitemoments. We employed the invariant properties of the Gaussian–Hermite moments discovered earlier in [1] and we showed how to construct rotation Gaussian–Hermite invariants even in the cases when no explicit invariants from geometric moments are available. We verify by experiments the rotation invariance and show that we are capable of computing much higher order of Gaussian–Hermite invariants than of geometric invariants, which brings better discrimination power.