In hyperspectral imaging, spectral signatures of objects are recorded for each image pixel. The spectral signature of an object is the reflectance variation or function with respect to the wavelength. It is important for characterizing materials and their properties. In hyperspectral imaging, different types of noise appear due to environmental or instrumental influences.
An approach to parameter optimization for the low-rank matrix recovery method in hyperspectral imaging is discussed. We formulate an optimization problem with respect to the initial parameters of the low-rank matrix recovery method. The performance for different parameter settings is compared in terms of computational times and memory. The results are evaluated by computing the peak signal-to-noise ratio as a quantitative measure. The potential improvement in the performance of the noise reduction method is discussed when optimizing the choice of the initial values. The optimization method is tested on standard and openly available hyperspectral data sets, including Indian Pines, Pavia Centre, and Pavia University.
Author
Monika Wolfmayr
Cite as
Wolfmayr M. Parameter Optimization for Low-Rank Matrix Recovery in Hyperspectral Imaging. Applied Sciences. 2023; 13(16):9373. https://doi.org/10.3390/app13169373
Publication
https://doi.org/10.3390/app13169373, https://www.mdpi.com/2076-3417/13/16/9373
Acknowledgements
This research was funded by the Regional Council of Central Finland/ Council of Tampere Region and European Regional Development Fund as part of the coADDVA—ADDing VAlue by Computing in Manufacturing projects of Jamk University of Applied Sciences. The project is funded by the REACT-EU Instrument as part of the European Union’s response to the COVID-19 pandemic.
