Shift-rotation absolute measurement method for irregular aperture optical surfaces based on deep learning

Absolute measurement technology has received considerable attention in the field of optical metrology owing to its high accuracy. However, to ensure accuracy of measurement, the traditional method requires the use of expensive high-precision stages and considerable time for the precise adjustment of...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Lili Yang, Jiantai Dou, Zhongming Yang, Zhaojun Liu
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Interferometry Surface measurement Deep learning Convolutional neural network Physics QC1-999
Acceso en línea:	https://doaj.org/article/9d55cef5de2f454db6dc9bae7a284189
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9d55cef5de2f454db6dc9bae7a284189
record_format	dspace
spelling	oai:doaj.org-article:9d55cef5de2f454db6dc9bae7a2841892021-11-24T04:28:58ZShift-rotation absolute measurement method for irregular aperture optical surfaces based on deep learning2211-379710.1016/j.rinp.2021.105020https://doaj.org/article/9d55cef5de2f454db6dc9bae7a2841892021-12-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2211379721010184https://doaj.org/toc/2211-3797Absolute measurement technology has received considerable attention in the field of optical metrology owing to its high accuracy. However, to ensure accuracy of measurement, the traditional method requires the use of expensive high-precision stages and considerable time for the precise adjustment of the measured surface. A shift-rotation absolute measurement method for irregular aperture optical surfaces based on deep learning is presented here. In this method, the measured surface needs to be tested in the original position and two randomly changed positions. Furthermore, a simple and effective shift-rotation prediction convolutional neural network that can learn the mapping relationships between the binarized images of the changed position and shift-rotation is designed. The shape of the measured surface with an irregularly shaped aperture is obtained by fitting orthogonalized Zernike polynomials. Compared with the current absolute measurement method for irregular apertures, this method is highly efficient and cost-effective for adjusting the measured surface. The simulation and experimental results demonstrate the accuracy and validity of this approach.Lili YangJiantai DouZhongming YangZhaojun LiuElsevierarticleInterferometrySurface measurementDeep learningConvolutional neural networkPhysicsQC1-999ENResults in Physics, Vol 31, Iss , Pp 105020- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Interferometry Surface measurement Deep learning Convolutional neural network Physics QC1-999
spellingShingle	Interferometry Surface measurement Deep learning Convolutional neural network Physics QC1-999 Lili Yang Jiantai Dou Zhongming Yang Zhaojun Liu Shift-rotation absolute measurement method for irregular aperture optical surfaces based on deep learning
description	Absolute measurement technology has received considerable attention in the field of optical metrology owing to its high accuracy. However, to ensure accuracy of measurement, the traditional method requires the use of expensive high-precision stages and considerable time for the precise adjustment of the measured surface. A shift-rotation absolute measurement method for irregular aperture optical surfaces based on deep learning is presented here. In this method, the measured surface needs to be tested in the original position and two randomly changed positions. Furthermore, a simple and effective shift-rotation prediction convolutional neural network that can learn the mapping relationships between the binarized images of the changed position and shift-rotation is designed. The shape of the measured surface with an irregularly shaped aperture is obtained by fitting orthogonalized Zernike polynomials. Compared with the current absolute measurement method for irregular apertures, this method is highly efficient and cost-effective for adjusting the measured surface. The simulation and experimental results demonstrate the accuracy and validity of this approach.
format	article
author	Lili Yang Jiantai Dou Zhongming Yang Zhaojun Liu
author_facet	Lili Yang Jiantai Dou Zhongming Yang Zhaojun Liu
author_sort	Lili Yang
title	Shift-rotation absolute measurement method for irregular aperture optical surfaces based on deep learning
title_short	Shift-rotation absolute measurement method for irregular aperture optical surfaces based on deep learning
title_full	Shift-rotation absolute measurement method for irregular aperture optical surfaces based on deep learning
title_fullStr	Shift-rotation absolute measurement method for irregular aperture optical surfaces based on deep learning
title_full_unstemmed	Shift-rotation absolute measurement method for irregular aperture optical surfaces based on deep learning
title_sort	shift-rotation absolute measurement method for irregular aperture optical surfaces based on deep learning
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/9d55cef5de2f454db6dc9bae7a284189
work_keys_str_mv	AT liliyang shiftrotationabsolutemeasurementmethodforirregularapertureopticalsurfacesbasedondeeplearning AT jiantaidou shiftrotationabsolutemeasurementmethodforirregularapertureopticalsurfacesbasedondeeplearning AT zhongmingyang shiftrotationabsolutemeasurementmethodforirregularapertureopticalsurfacesbasedondeeplearning AT zhaojunliu shiftrotationabsolutemeasurementmethodforirregularapertureopticalsurfacesbasedondeeplearning
_version_	1718415993445810176

Shift-rotation absolute measurement method for irregular aperture optical surfaces based on deep learning

Ejemplares similares