Abstract
While hyperspectral images typically contain two orders of magnitude more information about the detailed colour spectrum of the object under study compared to RGB images, this inevitably leads to larger storage costs and larger bandwidth requirements. This, in consequence, typically makes it challenging to use such images for real-time industrial defect detection. A second challenge of working with images having tens to hundreds of colour channels is that most available deep-learning (DL) networks are designed for images with three colours. In this paper, we will demonstrate that training typical DL segmentation networks on the full hyperspectral colour channel stack performs differently than when training on only three channels. We will also test two different approaches (Greedy Selection and Bayesian Optimization) to select the N-best wavelengths. For a given use-case, we demonstrate how optimal 3-wavelength images can outperform baseline wavelength selection methods as RGB and PCA (principal component analysis) as well as outperform networks trained with the full colour channel stack.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Balandat, M., et al.: BoTorch: a framework for efficient Monte-Carlo Bayesian optimization (2019). https://doi.org/10.48550/ARXIV.1910.06403
Gendreau, M., Potvin., J.: Handbook of Metaheuristics, Springer, New York (2019). https://doi.org/10.1007/978-1-4419-1665-5, ISBN 978-3-319-91085-7
Genser, N., Seiler, J., Kaup, A.: Camera Array for Multi-Spectral Imaging. In: IEEE Transactions on Image Processing, vol. 29 (2020)
Ghamisi, P., et al.: Advances in hyperspectral image and signal processing: a comprehensive overview of the state of the art. IEEE Geosci. Remote Sens. Mag. 5(4), 37–78 (2017)
Iakubovskii, P.: Segmentation Models Pytorch. https://github.com/qubvel/segmentation_models.pytorch. Accessed 13 Feb 2023
Jolliffe, I.T: Principal Component Analysis. Springer Series in Statistics. Springer-Verlag, New York (2002). https://doi.org/10.1007/b98835
Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection (2016). https://doi.org/10.48550/ARXIV.1612.03144
Liu, D., Sun, D.-W., Zeng, X.-A.: Recent advances in wavelength selection techniques for hyperspectral image processing in the food industry. Food Bioprocess Technol. 7(2), 307–323 (2014). https://doi.org/10.1007/s11947-013-1193-6
Liu, Y., Zhou, S., Han, W., Liu, W., Qiu, Z., Li, C.: Convolutional neural network for hyperspectral data analysis and effective wavelengths selection. Anal. Chim. Acta 1086, 46–54 (2019) https://doi.org/10.1016/j.aca.2019.08.026
Mehmood, T., Liland, K.H., Snipen, L., Sæbø, S.: A review of variable selection methods in partial least squares regression. Chemom. Intell. Lab. Syst. 118, 62–69 (2012). https://doi.org/10.1016/j.chemolab.2012.07.010
Schumacher, P., Gruna, R., Längle, T., Beyerer, J.: Problem-specific optimized multispectral sensing for improved quantification of plant biochemical constituents. In: 2022 12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS), pp. 1–6, Rome, Italy (2022). https://doi.org/10.1109/WHISPERS56178.2022.9955113
Signoroni, A., Savardi, M., Baronio, A., Benini, S.: Deep learning meets hyperspectral image analysis: a multidisciplinary review. J. Imaging 5(5), 52 (2019). https://doi.org/10.3390/jimaging5050052
Sonobe, R., et al. Hyperspectral wavelength selection for estimating chlorophyll content of muskmelon leaves. Eur. J. Remote Sens. 54(1), 513–524 (2021). https://doi.org/10.1080/22797254.2021.1964383
Tan, M., Le, Q.V.: EfficientNet: rethinking model scaling for convolutional neural networks (2019). https://doi.org/10.48550/ARXIV.1905.11946
Varga, L.A., Makowski, J., Zell, A.: Measuring the ripeness of fruit with hyperspectral imaging and deep learning. In: Proceedings of the International Joint Conference on Neural Networks (2021). https://doi.org/10.1109/IJCNN52387.2021.9533728
Zhu, S., Zhou, L., Gao, P., Bao, Y., He, Y., Feng, L.: Near-infrared hyperspectral imaging combined with deep learning to identify cotton seed varieties. Molecules (Basel, Switzerland) 24(18), 3268 (2019). https://doi.org/10.3390/molecules24183268
Acknowledgements
This research is supported by Flanders Make, the strategic research Centre for the Manufacturing Industry and the Flemish Innovation and Entrepreneurship Agency through the research project ‘DAP2CHEM’ (project number: HBC.2020.2455). The authors would like to thank all project’s partners for their inputs and support to make this publication.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Dehaeck, S., Van Belleghem, R., Wouters, N., De Ketelaere, B., Liao, W. (2023). Optimal Wavelength Selection for Deep Learning from Hyperspectral Images. In: Pertusa, A., Gallego, A.J., Sánchez, J.A., Domingues, I. (eds) Pattern Recognition and Image Analysis. IbPRIA 2023. Lecture Notes in Computer Science, vol 14062. Springer, Cham. https://doi.org/10.1007/978-3-031-36616-1_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-36616-1_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-36615-4
Online ISBN: 978-3-031-36616-1
eBook Packages: Computer ScienceComputer Science (R0)