A novel set of rotationally and translationally invariant features for images based on the non-commutative bispectrum
read the original abstract
We propose a new set of rotationally and translationally invariant features for image or pattern recognition and classification. The new features are cubic polynomials in the pixel intensities and provide a richer representation of the original image than most existing systems of invariants. Our construction is based on the generalization of the concept of bispectrum to the three-dimensional rotation group SO(3), and a projection of the image onto the sphere.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
bispectrum: Selective $G$-Bispectra Made Practical
bispectrum library delivers selective G-bispectra for seven groups with reduced costs (O(|G|) for finite groups, O(L^2) for spheres), sub-millisecond GPU times, and superior benchmark performance versus standard pooli...
-
Machine-learning modeling of magnetization dynamics in quasi-equilibrium and driven metallic spin systems
Generalized ML force fields reproduce non-collinear magnetic orders on lattices and predict voltage-driven domain-wall motion in itinerant magnets using extensions to nonequilibrium torques.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.