A3 Book section, Chapters in research books
Method for Radiance Approximation of Hyperspectral Data Using Deep Neural Network (2023)

Rahkonen, S., & Pölönen, I. (2023). Method for Radiance Approximation of Hyperspectral Data Using Deep Neural Network. In P. Neittaanmäki, & M.-L. Rantalainen (Eds.), Impact of Scientific Computing on Science and Society (pp. 315-325). Springer. Computational Methods in Applied Sciences, 58. https://doi.org/10.1007/978-3-031-29082-4_18

JYU authors or editors

Rahkonen, Samuli
Pölönen, Ilkka

Publication details

All authors or editors: Rahkonen, Samuli; Pölönen, Ilkka

Parent publication: Impact of Scientific Computing on Science and Society

Parent publication editors: Neittaanmäki, Pekka; Rantalainen, Marja-Leena

ISBN: 978-3-031-29081-7

eISBN: 978-3-031-29082-4

Journal or series: Computational Methods in Applied Sciences

ISSN: 1871-3033

eISSN: 2543-0203

Publication year: 2023

Number in series: 58

Pages range: 315-325

Number of pages in the book: 450

Publisher: Springer

Place of Publication: Cham

Publication country: Switzerland

Publication language: English

DOI: https://doi.org/10.1007/978-3-031-29082-4_18

Publication open access: Not open

Publication channel open access:

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/92599

Abstract

We propose a neural network model for calculating the radiance from raw hyperspectral data gathered using a Fabry–Perot interferometer color camera developed by VTT Technical Research Centre of Finland. The hyperspectral camera works by taking multiple images from different wavelength with varying interferometer settings. The raw data needs to be converted to radiance in order to make any use of it, but this leads to larger file sizes. Because of the amount of the data and the structure of the raw data, the processing has to be run in parallel, requiring a lot of memory and time. Using raw camera data could save processing time and file space in applications with computation time requirements. Secondly, this kind of neural network could be used for generating synthetic training data or use it in generative models. The proposed model approaches these problems by combining spatial and spectral-wise convolutions in neural network with minimizing a loss function utilizing the spectral distance and mean squared loss. The used dataset included images from many patients with melanoma skin cancer.

Keywords: machine learning; modelling (representation)

Free keywords: spectral imaging; modelling; machine learning; data processing

Fields of science: