Gradient-Descent-like Ghost Imaging

Ghost imaging is an indirect optical imaging technique, which retrieves object information by calculating the intensity correlation between reference and bucket signals. However, in existing correlation functions, a high number of measurements is required to acquire a satisfied performance, and the...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Wen-Kai Yu, Chen-Xi Zhu, Ya-Xin Li, Shuo-Fei Wang, Chong Cao
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	ghost imaging gradient-descent image reconstruction iteration image quality denoising Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/e0b4349532f14f8db88164fef2b22fd8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e0b4349532f14f8db88164fef2b22fd8
record_format	dspace
spelling	oai:doaj.org-article:e0b4349532f14f8db88164fef2b22fd82021-11-25T18:57:27ZGradient-Descent-like Ghost Imaging10.3390/s212275591424-8220https://doaj.org/article/e0b4349532f14f8db88164fef2b22fd82021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7559https://doaj.org/toc/1424-8220Ghost imaging is an indirect optical imaging technique, which retrieves object information by calculating the intensity correlation between reference and bucket signals. However, in existing correlation functions, a high number of measurements is required to acquire a satisfied performance, and the increase in measurement number only leads to limited improvement in image quality. Here, inspired by the gradient descent idea that is widely used in artificial intelligence, we propose a gradient-descent-like ghost imaging method to recursively move towards the optimal solution of the preset objective function, which can efficiently reconstruct high-quality images. The feasibility of this technique has been demonstrated in both numerical simulation and optical experiments, where the image quality is greatly improved within finite steps. Since the correlation function in the iterative formula is replaceable, this technique offers more possibilities for image reconstruction of ghost imaging.Wen-Kai YuChen-Xi ZhuYa-Xin LiShuo-Fei WangChong CaoMDPI AGarticleghost imaginggradient-descentimage reconstructioniterationimage qualitydenoisingChemical technologyTP1-1185ENSensors, Vol 21, Iss 7559, p 7559 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	ghost imaging gradient-descent image reconstruction iteration image quality denoising Chemical technology TP1-1185
spellingShingle	ghost imaging gradient-descent image reconstruction iteration image quality denoising Chemical technology TP1-1185 Wen-Kai Yu Chen-Xi Zhu Ya-Xin Li Shuo-Fei Wang Chong Cao Gradient-Descent-like Ghost Imaging
description	Ghost imaging is an indirect optical imaging technique, which retrieves object information by calculating the intensity correlation between reference and bucket signals. However, in existing correlation functions, a high number of measurements is required to acquire a satisfied performance, and the increase in measurement number only leads to limited improvement in image quality. Here, inspired by the gradient descent idea that is widely used in artificial intelligence, we propose a gradient-descent-like ghost imaging method to recursively move towards the optimal solution of the preset objective function, which can efficiently reconstruct high-quality images. The feasibility of this technique has been demonstrated in both numerical simulation and optical experiments, where the image quality is greatly improved within finite steps. Since the correlation function in the iterative formula is replaceable, this technique offers more possibilities for image reconstruction of ghost imaging.
format	article
author	Wen-Kai Yu Chen-Xi Zhu Ya-Xin Li Shuo-Fei Wang Chong Cao
author_facet	Wen-Kai Yu Chen-Xi Zhu Ya-Xin Li Shuo-Fei Wang Chong Cao
author_sort	Wen-Kai Yu
title	Gradient-Descent-like Ghost Imaging
title_short	Gradient-Descent-like Ghost Imaging
title_full	Gradient-Descent-like Ghost Imaging
title_fullStr	Gradient-Descent-like Ghost Imaging
title_full_unstemmed	Gradient-Descent-like Ghost Imaging
title_sort	gradient-descent-like ghost imaging
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/e0b4349532f14f8db88164fef2b22fd8
work_keys_str_mv	AT wenkaiyu gradientdescentlikeghostimaging AT chenxizhu gradientdescentlikeghostimaging AT yaxinli gradientdescentlikeghostimaging AT shuofeiwang gradientdescentlikeghostimaging AT chongcao gradientdescentlikeghostimaging
_version_	1718410496235798528

Gradient-Descent-like Ghost Imaging

Ejemplares similares