Institute of Information Theory and Automation

Publication details

Implicit Moment Invariants

Journal Article

Flusser Jan, Kautský J., Šroubek Filip


serial: International Journal of Computer Vision vol.86, 1 (2010), p. 72-86

research: CEZ:AV0Z10750506

project(s): 1M0572, GA MŠk, GA102/08/1593, GA ČR

keywords: Implicit invariants, Orthogonal polynomials, Polynomial image deformation

preview: Download

abstract (eng):

The use of traditional moment invariants in object recognition is limited to simple geometric transforms, such as rotation, scaling and affine transformation of the image. This paper introduces so-called implicit moment invariants. Implicit invariants measure the similarity between two images factorized by admissible image deformations. For many types of image deformations traditional invariants do not exist but implicit invariants can be used as features for object recognition. In the paper we present implicit moment invariants with respect to polynomial transform of spatial coordinates, describe their stable and efficient implementation bymeans of orthogonal moments, and demonstrate their performance in artificial as well as real experiments.

abstract (cze):

Tradiční momentové invarianty jsou omezeny pouze na jednoduché transformace rozpoznávaných objektů, jako je rotace, změna meřítka či afinní transformace. V tomto článku zavádíme tzv "implicitní momentové invarianty" vzhledem k polynomialním deformacím objektu. Je vysvětlena nejen příslušná teorie, ale i efektivní implementace pomocí ortogonalních momentů.

RIV: BD

Responsible for information: admin
Last modification: 21.12.2012
Institute of Information Theory and Automation