Efficient anisotropic scaling and translation invariants of Tchebichef moments using image normalization

•Simplify invariant algorithms using orthogonal properties of basis functions.•Fast computation of moment invariants using a new set of recurrence relations.•New normalization scheme for anisotropic scaling and translation invariants.•Features with better discriminative power and resilience to noise...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition letters Vol. 169; pp. 8 - 16
Main Authors: Pee, Chih-Yang, Ong, S.H., Raveendran, P., Wong, L.K.
Format: Journal Article
Language:English
Published: Elsevier B.V 01.05.2023
Subjects:
Anisotropic scaling and translation invariant
Discrete orthogonal moment
Image normalization
Moment invariant
Pattern classification
Tchebichef moment
Discrete orthogonal moment
Anisotropic scaling and translation invariant
Image normalization
Tchebichef moment
Pattern classification
Moment invariant
ISSN:0167-8655, 1872-7344
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Simplify invariant algorithms using orthogonal properties of basis functions.•Fast computation of moment invariants using a new set of recurrence relations.•New normalization scheme for anisotropic scaling and translation invariants.•Features with better discriminative power and resilience to noise. [Display omitted] Anisotropic scaling and translation invariants of Tchebichef moments are commonly used in image analysis to address issues arising from patterns distorted by non-uniform scaling and translation. In this paper, we formulate a new fast computational algorithm and a new normalization scheme based on the properties of Tchebichef moments. The proposed model can correctly resolve the mirror reflection ambiguities caused by the scaling transformations and gives smaller size deviations for various patterns so that the canonical form can easily fit within the normalized space. An empirical study shows that the proposed method significantly improves numerical computation and classification accuracy under non-noisy and noisy conditions when compared with existing methods. The main contribution of this paper is a novel fast computational algorithm for anisotropic scaling and translation invariants of Tchebichef moments and a new normalization scheme that produces features with higher discriminative power. The proposed algorithm is useful for recognizing objects with non-uniform size and displacement deformations. It is also a key component in formulating a better affine invariant algorithm for the image analysis community.
ISSN:0167-8655
1872-7344
DOI:10.1016/j.patrec.2023.03.015