Deep learning super resolution for high-speed excitation emission matrix measurements

Michelucci, Umberto; Fluri, Silvan; Baumgartner, Michael; Venturini, Francesca

doi:10.1117/12.2647589

Publication type:	Conference paper
Type of review:	Peer review (publication)
Title:	Deep learning super resolution for high-speed excitation emission matrix measurements
Authors:	Michelucci, Umberto Fluri, Silvan Baumgartner, Michael Venturini, Francesca
et. al:	No
DOI:	10.1117/12.2647589
Proceedings:	AI and Optical Data Sciences IV
Editors of the parent work:	Jalali, Bahram Kitayama, Ken-ichi
Volume(Issue):	12438
Conference details:	SPIE Photonics West, San Francisco, USA, 28 January - 2 February 2023
Issue Date:	Mar-2023
Publisher / Ed. Institution:	SPIE
ISBN:	9781510659810 9781510659827
Language:	English
Subjects:	Super-resolution; Deep learning; Machine learning; Fluorescence spectroscopy; Excitation-emission matrix; Olive oil; Food technology
Subject (DDC):	006: Special computer methods 540: Chemistry
Abstract:	In many optical experiments, a long measurement time is necessary to collect enough information and improve the signal-to-noise ratio. This happens, for example, in total luminescence spectroscopy (TLS) where the data is acquired as excitation-emission matrices (EEMs). An EEM is an unique chemical fingerprint of the analyzed substance that allows its comprehensive characterization. To collect a high-resolution EEM, it is necessary to scan both the excitation and the emission wavelengths in small steps and, for each step, to collect the light for a long time to maximize the signal-to-noise ratio. Therefore, acquiring a high-resolution excitation emission matrix can take more than an hour, depending on the size of the wavelength steps, the intensity of the signal, and the spectral range to be analyzed. This paper proposes a new method to reconstruct a high-resolution EEM from low-resolution one using deep learning super-resolution techniques. Specifically, this work proposes a new artificial neural network architecture, a sub-pixel convolutional neural network, designed to be applied to fluorescence EEM images. The code used is made available via a GitHub repository with instructions for applying transfer learning to different types of images.
URI:	https://digitalcollection.zhaw.ch/handle/11475/27608
Fulltext version:	Published version
License (according to publishing contract):	Licence according to publishing contract
Departement:	School of Engineering
Organisational Unit:	Institute of Applied Mathematics and Physics (IAMP)
Published as part of the ZHAW project:	ARES - AI for fluoREscence Spectroscopy in oil
Appears in collections:	Publikationen School of Engineering

Files in This Item:

There are no files associated with this item.

Show full item record

Michelucci, U., Fluri, S., Baumgartner, M., & Venturini, F. (2023). Deep learning super resolution for high-speed excitation emission matrix measurements [Conference paper]. In B. Jalali & K.-i. Kitayama (Eds.), AI and Optical Data Sciences IV (Vol. 12438). SPIE. https://doi.org/10.1117/12.2647589

Michelucci, U. et al. (2023) ‘Deep learning super resolution for high-speed excitation emission matrix measurements’, in B. Jalali and K.-i. Kitayama (eds) AI and Optical Data Sciences IV. SPIE. Available at: https://doi.org/10.1117/12.2647589.

U. Michelucci, S. Fluri, M. Baumgartner, and F. Venturini, “Deep learning super resolution for high-speed excitation emission matrix measurements,” in AI and Optical Data Sciences IV, Mar. 2023, vol. 12438. doi: 10.1117/12.2647589.

MICHELUCCI, Umberto, Silvan FLURI, Michael BAUMGARTNER und Francesca VENTURINI, 2023. Deep learning super resolution for high-speed excitation emission matrix measurements. In: Bahram JALALI und Ken-ichi KITAYAMA (Hrsg.), AI and Optical Data Sciences IV. Conference paper. SPIE. März 2023. ISBN 9781510659810

Michelucci, Umberto, Silvan Fluri, Michael Baumgartner, and Francesca Venturini. 2023. “Deep Learning Super Resolution for High-Speed Excitation Emission Matrix Measurements.” Conference paper. In AI and Optical Data Sciences IV, edited by Bahram Jalali and Ken-ichi Kitayama. Vol. 12438. SPIE. https://doi.org/10.1117/12.2647589.

Michelucci, Umberto, et al. “Deep Learning Super Resolution for High-Speed Excitation Emission Matrix Measurements.” AI and Optical Data Sciences IV, edited by Bahram Jalali and Ken-ichi Kitayama, vol. 12438, SPIE, 2023, https://doi.org/10.1117/12.2647589.