The hybrid approach -- Convolutional Neural Networks and Expectation Maximization Algorithm -- for Tomographic Reconstruction of Hyperspectral Images

Mads Juul Ahlebaek*, Mads Svanborg Peters, Wei-Chih Huang, Mads Toudal Frandsen, René L. Eriksen, Bjarke Jørgensen

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearch

34 Downloads (Pure)

Abstract

We present a simple but novel hybrid approach to hyperspectral data cube reconstruction from computed tomography imaging spectrometry (CTIS) images that sequentially combines neural networks and the iterative Expectation Maximization (EM) algorithm. We train and test the ability of the method to reconstruct data cubes of 100×100×25 and 100×100×100 voxels, corresponding to 25 and 100 spectral channels, from simulated CTIS images generated by our CTIS simulator. The hybrid approach utilizes the inherent strength of the Convolutional Neural Network (CNN) with regard to noise and its ability to yield consistent reconstructions and make use of the EM algorithm's ability to generalize to spectral images of any object without training. The hybrid approach achieves better performance than both the CNNs and EM alone for seen (included in CNN training) and unseen (excluded from CNN training) cubes for both the 25- and 100-channel cases. For the 25 spectral channels, the improvements from CNN to the hybrid model (CNN + EM) in terms of the mean-squared errors are between 14-26%. For 100 spectral channels, the improvements between 19-40% are attained with the largest improvement of 40% for the unseen data, to which the CNNs are not exposed during the training.
Original languageEnglish
Article number a1
JournalJournal of Spectral Imaging
Volume12
Number of pages20
ISSN2040-4565
DOIs
Publication statusPublished - 2023
EventIASIM 2022, July 2022, Esbjerg, Denmark - Esbjerg, Denmark
Duration: 3. Jun 20226. Feb 2024

Conference

ConferenceIASIM 2022, July 2022, Esbjerg, Denmark
Country/TerritoryDenmark
CityEsbjerg
Period03/06/202206/02/2024

Keywords

  • artificial neural networks
  • convolutional neural networks
  • hyperspectral imaging
  • snapshot
  • tomographic reconstruction

Fingerprint

Dive into the research topics of 'The hybrid approach -- Convolutional Neural Networks and Expectation Maximization Algorithm -- for Tomographic Reconstruction of Hyperspectral Images'. Together they form a unique fingerprint.

Cite this