Journal of Spectral Imaging JSI—Journal of Spectral Imaging is an online, Open Access, peer-review journal publishing high-quality papers in the rapidly growing field of spectral, hyperspectral and chemical imaging. https://www.impopen.com/jsi-toc/12 IM Publications Open en © IM Publications Open LLP Journal of Spectral Imaging 2040-4565 © IM Publications Open LLP [email protected] Estimation of pigment concentration in LDPE via in-line hyperspectral imaging and machine learning https://doi.org/10.1255/jsi.2023.a2 Due to the increasing amount of plastic waste and high-quality demands on recycled plastic interest for in-line composition estimation in plastics has grown the last few years. This study investigates pigment blue 15 : 3 with varying concentrations in LDPE. Samples are investigated with two industrial hyperspectral imaging systems where one has the hyperspectral range from 450 nm to 1050 nm and the other from 950 nm to 1750 nm. A model based on peak ratios of selected bands and model based on a principal component analysis have been tested. The models only predict pigment concentrations between 40.0 wt% and 1.7 × 10–3 wt% if both spectral ranges are combined. Unknown samples containing pigment concentration ranging from 20 wt% to 0.31 wt% were predicted and correlated to the actual pigment concentrations (R2 = 0.977) and the PC-based model outperforms the peak ratio model. The studied approach can be a part of the solution to the plastic challenge and can be transferred to other applications where concentration determination is key. Estimation of pigment concentration in LDPE via in-line hyperspectral imaging and machine learning

J. Spectral Imaging 12, a2 (2023). doi:10.1255/jsi.2023.a2

Due to the increasing amount of plastic waste and high-quality demands on recycled plastic interest for in-line composition estimation in plastics has grown the last few years. This study investigates pigment blue 15 : 3 with varying concentrations in LDPE. Samples are investigated with two industrial hyperspectral imaging systems where one has the hyperspectral range from 450 nm to 1050 nm and the other from 950 nm to 1750 nm. A model based on peak ratios of selected bands and model based on a principal component analysis have been tested. The models only predict pigment concentrations between 40.0 wt% and 1.7 × 10–3 wt% if both spectral ranges are combined. Unknown samples containing pigment concentration ranging from 20 wt% to 0.31 wt% were predicted and correlated to the actual pigment concentrations (R2 = 0.977) and the PC-based model outperforms the peak ratio model. The studied approach can be a part of the solution to the plastic challenge and can be transferred to other applications where concentration determination is key.

]]> Estimation of pigment concentration in LDPE via in-line hyperspectral imaging and machine learning Georgiana Amariei Anne Sofie Schaarup-Kjær Pernille Klarskov Martin Lahn Henriksen Mogens Hinge doi:10.1255/jsi.2023.a2 J. Spectral Imaging 12, a2 (2023) 2023-04-03 Journal of Spectral Imaging 2023-04-03 12 1 11 10.1255/jsi.2023.a2 https://doi.org/10.1255/jsi.2023.a2 The hybrid approach—convolutional neural networks and expectation maximisation algorithm—for tomographic reconstruction of hyperspectral images https://doi.org/10.1255/jsi.2023.a1 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 maximisation (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 utilises the inherent strength of the Convolutional Neural Network (CNN) with regards to noise and its ability to yield consistent reconstructions and make use of the EM algorithm’s ability to generalise 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 % and 26 %. For 100 spectral channels, the improvements between 19 % and 40 % are attained with the largest improvement of 40 % for the unseen data, to which the CNNs are not exposed during the training. The hybrid approach—convolutional neural networks and expectation maximisation algorithm—for tomographic reconstruction of hyperspectral images

J. Spectral Imaging 12, a1 (2023). doi:10.1255/jsi.2023.a1

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 maximisation (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 utilises the inherent strength of the Convolutional Neural Network (CNN) with regards to noise and its ability to yield consistent reconstructions and make use of the EM algorithm’s ability to generalise 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 % and 26 %. For 100 spectral channels, the improvements between 19 % and 40 % are attained with the largest improvement of 40 % for the unseen data, to which the CNNs are not exposed during the training.

]]> The hybrid approach—convolutional neural networks and expectation maximisation algorithm—for tomographic reconstruction of hyperspectral images Mads Juul Ahlebæk Mads Svanborg Peters Wei-Chih Huang Mads Toudal Frandsen René Lynge Eriksen Bjarke Jørgensen doi:10.1255/jsi.2023.a1 J. Spectral Imaging 12, a1 (2023) 2023-01-31 Journal of Spectral Imaging 2023-01-31 12 1 20 10.1255/jsi.2023.a1 https://doi.org/10.1255/jsi.2023.a1