3D Non‑separable Moment Invariants and Their Use in Neural Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F24%3A00602709" target="_blank" >RIV/67985556:_____/24:00602709 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/article/10.1007/s42979-024-03504-x" target="_blank" >https://link.springer.com/article/10.1007/s42979-024-03504-x</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s42979-024-03504-x" target="_blank" >10.1007/s42979-024-03504-x</a>

Jazyk výsledku

angličtina

Název v původním jazyce

3D Non‑separable Moment Invariants and Their Use in Neural Networks

Popis výsledku v původním jazyce

Recognition of 3D objects is an important task in many bio-medical and industrial applications. The recognition algorithms should work regardless of a particular orientation of the object in the space. In this paper, we introduce new 3D rotation moment invariants, which are composed of non-separable Appell moments. We show that non-separable moments may outperform the separable ones in terms of recognition power and robustness thanks to a better distribution of their zero surfaces over the image space. We test the numerical properties and discrimination power of the proposed invariants on three real datasets—MRI images of human brain, 3D scans of statues, and confocal microscope images of worms. We show the robustness to resampling errors improved more than twice and the recognition rate increased by 2–10 % comparing to most common descriptors. In the last section, we show how these invariants can be used in state-of-the-art neural networks for image recognition. The proposed H-NeXtA architecture improved the recognition rate by 2–5 % over the current networks.

Název v anglickém jazyce

3D Non‑separable Moment Invariants and Their Use in Neural Networks

Popis výsledku anglicky

Recognition of 3D objects is an important task in many bio-medical and industrial applications. The recognition algorithms should work regardless of a particular orientation of the object in the space. In this paper, we introduce new 3D rotation moment invariants, which are composed of non-separable Appell moments. We show that non-separable moments may outperform the separable ones in terms of recognition power and robustness thanks to a better distribution of their zero surfaces over the image space. We test the numerical properties and discrimination power of the proposed invariants on three real datasets—MRI images of human brain, 3D scans of statues, and confocal microscope images of worms. We show the robustness to resampling errors improved more than twice and the recognition rate increased by 2–10 % comparing to most common descriptors. In the last section, we show how these invariants can be used in state-of-the-art neural networks for image recognition. The proposed H-NeXtA architecture improved the recognition rate by 2–5 % over the current networks.

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA24-10069S" target="_blank" >GA24-10069S: Hybridní architektury neuronových sítí pro rozpoznávání obrazu</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

SN Computer Science

ISSN

2662-995X

e-ISSN

2661-8907

Svazek periodika

5

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

SG - Singapurská republika

Počet stran výsledku

16

Strana od-do

1166

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85211784939