Flexible Moment-Invariant Bases from Irreducible Tensors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bujack, Roxana, Shinkle, Emily, Allen, Alice, Suk, Tomas, Lubbers, Nicholas
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912306342920192
author Bujack, Roxana
Shinkle, Emily
Allen, Alice
Suk, Tomas
Lubbers, Nicholas
author_facet Bujack, Roxana
Shinkle, Emily
Allen, Alice
Suk, Tomas
Lubbers, Nicholas
contents Moment invariants are a powerful tool for the generation of rotation-invariant descriptors needed for many applications in pattern detection, classification, and machine learning. A set of invariants is optimal if it is complete, independent, and robust against degeneracy in the input. In this paper, we show that the current state of the art for the generation of these bases of moment invariants, despite being robust against moment tensors being identically zero, is vulnerable to a degeneracy that is common in real-world applications, namely spherical functions. We show how to overcome this vulnerability by combining two popular moment invariant approaches: one based on spherical harmonics and one based on Cartesian tensor algebra.
format Preprint
id arxiv_https___arxiv_org_abs_2503_21939
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Flexible Moment-Invariant Bases from Irreducible Tensors
Bujack, Roxana
Shinkle, Emily
Allen, Alice
Suk, Tomas
Lubbers, Nicholas
Computer Vision and Pattern Recognition
Moment invariants are a powerful tool for the generation of rotation-invariant descriptors needed for many applications in pattern detection, classification, and machine learning. A set of invariants is optimal if it is complete, independent, and robust against degeneracy in the input. In this paper, we show that the current state of the art for the generation of these bases of moment invariants, despite being robust against moment tensors being identically zero, is vulnerable to a degeneracy that is common in real-world applications, namely spherical functions. We show how to overcome this vulnerability by combining two popular moment invariant approaches: one based on spherical harmonics and one based on Cartesian tensor algebra.
title Flexible Moment-Invariant Bases from Irreducible Tensors
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.21939