Characterization of the displacement response in chromatic confocal microscopy with a hybrid radial basis function network

Wenlong Lu, Cheng Chen, Jian Wang, Richard Leach, Chi Zhang, Xiaojun Liu, Zili Lei, Wenjun Yang, Xiangqian Jiang

Research output: Contribution to journalArticle

Abstract

Characterization of the displacement response is critical for accurate chromatic confocal measurement. Current characterization methods usually provide a linear or polynomial relationship between the extracted peak wavelengths of the spectral signal and displacement. However, these methods are susceptible to errors in the peak extraction algorithms and errors in the selected model. In this paper, we propose a hybrid radial basis function network method to characterise the displacement response. With this method, the peak wavelength of the spectral signal is firstly extracted with a state-of-art peak extraction algorithm, following which, a higher-accuracy chromatic dispersion model is applied to determine the displacement-wavelength relationship. Lastly, a radial basis function network is optimized to provide a mapping between the spectral signals and the residual fitting errors of the chromatic dispersion model. Using experimental tests, we show that the hybrid radial basis function network method significantly improves the measurement accuracy, when compared to the existing characterizing methods.

Original languageEnglish
Pages (from-to)22737-22752
Number of pages16
JournalOptics Express
Volume27
Issue number16
Early online date25 Jul 2019
DOIs
Publication statusPublished - 5 Aug 2019

Fingerprint

microscopy
wavelengths
polynomials

Cite this

Lu, Wenlong ; Chen, Cheng ; Wang, Jian ; Leach, Richard ; Zhang, Chi ; Liu, Xiaojun ; Lei, Zili ; Yang, Wenjun ; Jiang, Xiangqian. / Characterization of the displacement response in chromatic confocal microscopy with a hybrid radial basis function network. In: Optics Express. 2019 ; Vol. 27, No. 16. pp. 22737-22752.
@article{59c9e4876a004847b510f2906cb4542c,
title = "Characterization of the displacement response in chromatic confocal microscopy with a hybrid radial basis function network",
abstract = "Characterization of the displacement response is critical for accurate chromatic confocal measurement. Current characterization methods usually provide a linear or polynomial relationship between the extracted peak wavelengths of the spectral signal and displacement. However, these methods are susceptible to errors in the peak extraction algorithms and errors in the selected model. In this paper, we propose a hybrid radial basis function network method to characterise the displacement response. With this method, the peak wavelength of the spectral signal is firstly extracted with a state-of-art peak extraction algorithm, following which, a higher-accuracy chromatic dispersion model is applied to determine the displacement-wavelength relationship. Lastly, a radial basis function network is optimized to provide a mapping between the spectral signals and the residual fitting errors of the chromatic dispersion model. Using experimental tests, we show that the hybrid radial basis function network method significantly improves the measurement accuracy, when compared to the existing characterizing methods.",
keywords = "confocal microscopy, lenses, Chromatic confocal",
author = "Wenlong Lu and Cheng Chen and Jian Wang and Richard Leach and Chi Zhang and Xiaojun Liu and Zili Lei and Wenjun Yang and Xiangqian Jiang",
year = "2019",
month = "8",
day = "5",
doi = "10.1364/OE.27.022737",
language = "English",
volume = "27",
pages = "22737--22752",
journal = "Optics Express",
issn = "1094-4087",
publisher = "The Optical Society",
number = "16",

}

Characterization of the displacement response in chromatic confocal microscopy with a hybrid radial basis function network. / Lu, Wenlong; Chen, Cheng; Wang, Jian; Leach, Richard; Zhang, Chi; Liu, Xiaojun; Lei, Zili; Yang, Wenjun; Jiang, Xiangqian.

In: Optics Express, Vol. 27, No. 16, 05.08.2019, p. 22737-22752.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Characterization of the displacement response in chromatic confocal microscopy with a hybrid radial basis function network

AU - Lu, Wenlong

AU - Chen, Cheng

AU - Wang, Jian

AU - Leach, Richard

AU - Zhang, Chi

AU - Liu, Xiaojun

AU - Lei, Zili

AU - Yang, Wenjun

AU - Jiang, Xiangqian

PY - 2019/8/5

Y1 - 2019/8/5

N2 - Characterization of the displacement response is critical for accurate chromatic confocal measurement. Current characterization methods usually provide a linear or polynomial relationship between the extracted peak wavelengths of the spectral signal and displacement. However, these methods are susceptible to errors in the peak extraction algorithms and errors in the selected model. In this paper, we propose a hybrid radial basis function network method to characterise the displacement response. With this method, the peak wavelength of the spectral signal is firstly extracted with a state-of-art peak extraction algorithm, following which, a higher-accuracy chromatic dispersion model is applied to determine the displacement-wavelength relationship. Lastly, a radial basis function network is optimized to provide a mapping between the spectral signals and the residual fitting errors of the chromatic dispersion model. Using experimental tests, we show that the hybrid radial basis function network method significantly improves the measurement accuracy, when compared to the existing characterizing methods.

AB - Characterization of the displacement response is critical for accurate chromatic confocal measurement. Current characterization methods usually provide a linear or polynomial relationship between the extracted peak wavelengths of the spectral signal and displacement. However, these methods are susceptible to errors in the peak extraction algorithms and errors in the selected model. In this paper, we propose a hybrid radial basis function network method to characterise the displacement response. With this method, the peak wavelength of the spectral signal is firstly extracted with a state-of-art peak extraction algorithm, following which, a higher-accuracy chromatic dispersion model is applied to determine the displacement-wavelength relationship. Lastly, a radial basis function network is optimized to provide a mapping between the spectral signals and the residual fitting errors of the chromatic dispersion model. Using experimental tests, we show that the hybrid radial basis function network method significantly improves the measurement accuracy, when compared to the existing characterizing methods.

KW - confocal microscopy

KW - lenses

KW - Chromatic confocal

UR - http://www.scopus.com/inward/record.url?scp=85070306903&partnerID=8YFLogxK

U2 - 10.1364/OE.27.022737

DO - 10.1364/OE.27.022737

M3 - Article

C2 - 31510560

AN - SCOPUS:85070306903

VL - 27

SP - 22737

EP - 22752

JO - Optics Express

JF - Optics Express

SN - 1094-4087

IS - 16

ER -