Spectral reflectance curves for multispectral imaging, combining different techniques and a neural network

Fuente: Redalyc
Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: C.A. Osorio-Gómez
Format: Artículo científico
Sprache:en
Veröffentlicht: Sociedad Mexicana de Física A.C. 2009
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1876491479783833600
author C.A. Osorio-Gómez
author_facet C.A. Osorio-Gómez
contents Spectral reflectance curves for multispectral imaging, combining different techniques and a neural network C.A. Osorio-Gómez E. Mejía-Ospino J.E. Guerrero-Bermúdez Física, Astronomía y Matemáticas curve fitting multispectral imaging Artificia neural network spectral reflectance curves In this paper, we present an alternative procedure for the digital reconstruction of spectral reflectance curves of oil painting on canvas using multispectral imaging. The technique is based on a combination of the results obtained by pseudo-inverse, principal component analysis and interpolation; these results are the input to a feed-forward back propagation neural network fittin the values of the curves to a target obtained using a spectrophotometer Shimadzu UV2401. Goodness-of-Fit Coefficien (GFC), absolute mean error (ABE) and spectral Root Mean Squared error (RMS) are the metrics used to evaluate the performance of the procedure proposed. 2009 artículo científico 0035-001X https://www.redalyc.org/articulo.oa?id=57013231007 en http://www.redalyc.org/revista.oa?id=570 Revista Mexicana de Física application/pdf Sociedad Mexicana de Física A.C. Revista Mexicana de Física (México) Num.2 Vol.55
format Artículo científico
id redalyc_57013231007
institution Redalyc
language en
publishDate 2009
publisher Sociedad Mexicana de Física A.C.
spellingShingle Spectral reflectance curves for multispectral imaging, combining different techniques and a neural network
C.A. Osorio-Gómez
Física, Astronomía y Matemáticas
curve fitting
multispectral imaging
Artificia neural network
spectral reflectance curves
Spectral reflectance curves for multispectral imaging, combining different techniques and a neural network C.A. Osorio-Gómez E. Mejía-Ospino J.E. Guerrero-Bermúdez Física, Astronomía y Matemáticas curve fitting multispectral imaging Artificia neural network spectral reflectance curves In this paper, we present an alternative procedure for the digital reconstruction of spectral reflectance curves of oil painting on canvas using multispectral imaging. The technique is based on a combination of the results obtained by pseudo-inverse, principal component analysis and interpolation; these results are the input to a feed-forward back propagation neural network fittin the values of the curves to a target obtained using a spectrophotometer Shimadzu UV2401. Goodness-of-Fit Coefficien (GFC), absolute mean error (ABE) and spectral Root Mean Squared error (RMS) are the metrics used to evaluate the performance of the procedure proposed. 2009 artículo científico 0035-001X https://www.redalyc.org/articulo.oa?id=57013231007 en http://www.redalyc.org/revista.oa?id=570 Revista Mexicana de Física application/pdf Sociedad Mexicana de Física A.C. Revista Mexicana de Física (México) Num.2 Vol.55
title Spectral reflectance curves for multispectral imaging, combining different techniques and a neural network
topic Física, Astronomía y Matemáticas
curve fitting
multispectral imaging
Artificia neural network
spectral reflectance curves
url https://www.redalyc.org/articulo.oa?id=57013231007