Abstract
In this work, a frequency-based dimensionality reduction technique using variational mode decomposition (VMD) is proposed. Dimensionality reduction is a very important aspect of preprocessing in case of hyperspectral image (HSI) analysis where this step helps in elimination of the lesser informative bands, thereby reducing the size of the data and making its processing computationally less challenging. In contrast to the standard dimensionality reduction methods such as inter-band block correlation (IBBC) where bands are eliminated based on their similarity with the consecutive bands, the proposed method uses frequency information of each band to categorize it as a less or more informative band. In this way, only the topmost informative bands of HSI are selected to form the reduced dataset. In our experiment, in order to verify the efficiency of VMD as a dimensionality reduction technique, the hyperspectral unmixed results obtained for IBBC reduced dataset is compared with those obtained for VMD reduced dataset. From the parametric measures such as classification accuracy, root-mean-square error (RMSE) and visual results obtained after unmixing for both IBBC and VMD reduced datasets, it is noticed that the VMD reduced dataset performs better by achieving higher classification accuracy and lower RMSE than that of the existing IBBC method.
Similar content being viewed by others
References
Ablin, R., Sulochana, C.H.: Iterative-based visualization-oriented fusion scheme for hyperspectral images. Int. J. Signal Image Video Process. 12, 757–765 (2017)
Bhushan, D.B., Sowmya, V., Manikandan, M.S., Soman, K.: An effective pre-processing algorithm for detecting noisy spectral bands in hyperspectral imagery. In: Proceedings of International Symposium on Ocean Electronics, pp. 34–39 (2011)
Bieniarz, J.: Sparse methods for hyperspectral unmixing and image fusion. Ph.D. thesis (2016)
Candes, E.J., Wakin, M.B., Boyd, S.P.: Enhancing sparsity by reweighted l 1 minimization. J. Fourier Anal. Appl. 14(5–6), 877–905 (2008)
Cao, X., Wei, C., Han, J., Jiao, L.: Hyperspectral band selection using improved classification map. IEEE Geosci. Remote Sens. Lett. 14(11), 2147–2151 (2017)
Dragomiretskiy, K.: Variational methods in signal decomposition and image processing. Ph.D. thesis (2015)
Dragomiretskiy, K., Zosso, D.: Variational mode decomposition. IEEE Trans. Signal Process. 62(3), 531–544 (2014)
Fayyazi, H., Dehghani, H., Hosseini, M.: Spectral library pruning based on classification techniques. In: Proceedings of Conference on 8th Iranian Conference on Machine Vision and Image Processing (MVIP), pp. 141–144 (2013)
Iordache, M.D., Bioucas-Dias, J.M., Plaza, A.: Sparse unmixing of hyperspectral data. IEEE Trans. Geosci. Remote Sens. 49(6), 2014–2039 (2011)
Kolluru, P.K.: Svm based dimensionlity reduction and classification of hyperspectral data. Master’s thesis (2013)
Miguel, A., Riskin, E., Ladner, R., Barney, D.: Near-lossless and lossy compression of imaging spectrometer data: comparison of information extraction performance. Int. J. Signal Image Video Process. 6(1), 597–611 (2012)
Nechikkat, N., Sowmya, V., Soman, K.: A comparative analysis of variational mode and empirical mode features on hyperspectral image classification. Int. J. Appl. Eng. Res. (IJAER) 10(73), 95–98 (2015)
Reshma, R., Sowmya, V., Soman, K.: Dimensionality reduction using band selection technique for kernel based hyperspectral image classification. In: Proceedings of 6th International Conference on Advances In Computing and Communications, ICACC 2016, pp. 396–402 (2016)
Sharma, S., Dewal, M.L., Anand, R.S.: Performance evaluation of 3d hybrid transforms and 2d-set partitioning methods for lossy hyperspectral data compression. Int. J. Signal Image Video Process. 9(1), 1881–1888 (2015)
Su, H., Cai, Y., Du, Q.: Firefly-algorithm-inspired framework with band selection and extreme learning machine for hyperspectral image classification. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 10(1), 309–320 (2017)
Sun, W., Jiang, M., Li, W., Liu, Y.: A symmetric sparse representation based band selection method for hyperspectral imagery classification. Remote Sens. 8(238), 1–17 (2016)
Sun, W., Zhang, L., Zhang, L., Lai, Y.M.: A dissimilarity-weighted sparse self-representation method for band selection in hyperspectral imagery classification. IEEE J. Sel. Top. Appl. Observ. Remote Sens. 9(9), 4374–4388 (2016)
Sun, W., Tian, L., Xu, Y., Zhang, D., Du, Q.: Fast and robust self-representation method for hyperspectral band selection. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 10(11), 5087–5098 (2017)
Wang, N., Du, B., Zhang, L., Zhang, L.: An abundance characteristic-based independent component analysis for hyperspectral unmixing. IEEE Trans. Geosci. Remote Sens. 53(1), 416–428 (2015)
Zhu, F., Wang, Y., Fan, B., Meng, G., Pan, C.: Effective spectral unmixing via robust representation and learning-based sparsity. arXiv preprint arXiv:1409.0685 (2014)
Zhu, G., Huang, Y., Li, S., Tang, J., Liang, D.: Hyperspectral band selection via rank minimization. IEEE Geosci. Remote Sens. Lett. 14(12), 2320–2324 (2017)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Swarna, M., Sowmya, V. & Soman, K.P. Band selection using variational mode decomposition applied in sparsity-based hyperspectral unmixing algorithms. SIViP 12, 1463–1470 (2018). https://doi.org/10.1007/s11760-018-1301-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-018-1301-1