Cargando…

Comparison of Artificial Neural Network and Polynomial Approximation Models for Reflectance Spectra Reconstruction

Knowledge of surface reflection of an object is essential in many technological fields, including graphics and cultural heritage. Compared to direct multi- or hyper-spectral capturing approaches, commercial RGB cameras allow for a high resolution and fast acquisition, so the idea of mapping this inf...

Descripción completa

Detalles Bibliográficos
Autores principales: Lazar, Mihael, Hladnik, Aleš
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9866892/
https://www.ncbi.nlm.nih.gov/pubmed/36679797
http://dx.doi.org/10.3390/s23021000
_version_ 1784876205004029952
author Lazar, Mihael
Hladnik, Aleš
author_facet Lazar, Mihael
Hladnik, Aleš
author_sort Lazar, Mihael
collection PubMed
description Knowledge of surface reflection of an object is essential in many technological fields, including graphics and cultural heritage. Compared to direct multi- or hyper-spectral capturing approaches, commercial RGB cameras allow for a high resolution and fast acquisition, so the idea of mapping this information into a reflectance spectrum (RS) is promising. This study compared two modelling approaches based on a training set of RGB-reflectance pairs, one implementing artificial neural networks (ANN) and the other one using multivariate polynomial approximation (PA). The effect of various parameters was investigated: the ANN learning algorithm—standard backpropagation (BP) or Levenberg-Marquardt (LM), the number of hidden layers (HLs) and neurons, the degree of multivariate polynomials in PA, the number of inputs, and the training set size on both models. In the two-layer ANN with significantly fewer inputs than outputs, a better MSE performance was found where the number of neurons in the first HL was smaller than in the second one. For ANNs with one and two HLs with the same number of neurons in the first layer, the RS reconstruction performance depends on the choice of BP or LM learning algorithm. RS reconstruction methods based on ANN and PA are comparable, but the ANN models’ better fine-tuning capabilities enable, under realistic constraints, finding ANNs that outperform PA models. A profiling approach was proposed to determine the initial number of neurons in HLs—the search centre of ANN models for different training set sizes.
format Online
Article
Text
id pubmed-9866892
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-98668922023-01-22 Comparison of Artificial Neural Network and Polynomial Approximation Models for Reflectance Spectra Reconstruction Lazar, Mihael Hladnik, Aleš Sensors (Basel) Article Knowledge of surface reflection of an object is essential in many technological fields, including graphics and cultural heritage. Compared to direct multi- or hyper-spectral capturing approaches, commercial RGB cameras allow for a high resolution and fast acquisition, so the idea of mapping this information into a reflectance spectrum (RS) is promising. This study compared two modelling approaches based on a training set of RGB-reflectance pairs, one implementing artificial neural networks (ANN) and the other one using multivariate polynomial approximation (PA). The effect of various parameters was investigated: the ANN learning algorithm—standard backpropagation (BP) or Levenberg-Marquardt (LM), the number of hidden layers (HLs) and neurons, the degree of multivariate polynomials in PA, the number of inputs, and the training set size on both models. In the two-layer ANN with significantly fewer inputs than outputs, a better MSE performance was found where the number of neurons in the first HL was smaller than in the second one. For ANNs with one and two HLs with the same number of neurons in the first layer, the RS reconstruction performance depends on the choice of BP or LM learning algorithm. RS reconstruction methods based on ANN and PA are comparable, but the ANN models’ better fine-tuning capabilities enable, under realistic constraints, finding ANNs that outperform PA models. A profiling approach was proposed to determine the initial number of neurons in HLs—the search centre of ANN models for different training set sizes. MDPI 2023-01-15 /pmc/articles/PMC9866892/ /pubmed/36679797 http://dx.doi.org/10.3390/s23021000 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Lazar, Mihael
Hladnik, Aleš
Comparison of Artificial Neural Network and Polynomial Approximation Models for Reflectance Spectra Reconstruction
title Comparison of Artificial Neural Network and Polynomial Approximation Models for Reflectance Spectra Reconstruction
title_full Comparison of Artificial Neural Network and Polynomial Approximation Models for Reflectance Spectra Reconstruction
title_fullStr Comparison of Artificial Neural Network and Polynomial Approximation Models for Reflectance Spectra Reconstruction
title_full_unstemmed Comparison of Artificial Neural Network and Polynomial Approximation Models for Reflectance Spectra Reconstruction
title_short Comparison of Artificial Neural Network and Polynomial Approximation Models for Reflectance Spectra Reconstruction
title_sort comparison of artificial neural network and polynomial approximation models for reflectance spectra reconstruction
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9866892/
https://www.ncbi.nlm.nih.gov/pubmed/36679797
http://dx.doi.org/10.3390/s23021000
work_keys_str_mv AT lazarmihael comparisonofartificialneuralnetworkandpolynomialapproximationmodelsforreflectancespectrareconstruction
AT hladnikales comparisonofartificialneuralnetworkandpolynomialapproximationmodelsforreflectancespectrareconstruction