Abstract
Hyperspectral images (HSIs) are typically developed to obtain essential details about the land captured by hundreds of tiny and spectral bands. The classification does not achieve the desired performance using HSI dataset due to a large number of bands. Techniques for band reduction are utilized for the enhancement of classification performance. In this work, we propose an improved Truncated Singular Value Decomposition (TSVD), a classical feature extraction method, based on the supremacy of band segmentation in the HSI analysis. We call our method as Segmented-Truncated-SVD (STSVD), where the TSVD application extracts better local intrinsic and global properties from the HSI. Rather than applying the full dataset, we first segment the entire dataset into a number of strongly correlated spectral band subgroups and apply the TSVD on each subgroup separately. For Per-pixel classification by support vector machine (SVM) STSVD method, the classical PCA, Segmented-PCA (SPCA), SVD, and TSVD methods are applied to the mixed agricultural Indian Pines HSI dataset. The experimental results exhibit that the overall classification of STSVD (87.373%) remarkably outperforms all the other investigated methods: PCA (83.554%), SPCA (86.774%), SVD (83.986%), TSVD (83.526%), and the complete dataset without employing any feature reduction method (82.997%). The proposed STSVD also demands the least space complexities in different phases.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Richards, J.A., Jia, X.: Multispectral transformations of image data. In: Remote Sensing Digital Image Analysis: An Introduction, pp. 137–163 (2006)
Zabalza, J., et al.: Novel folded-pca for improved feature extraction and data reduction with hyperspectral imaging and sar in remote sensing. ISPRS J. Photogram. Remote Sens. 93, 112–122 (2014)
Uddin, M., Mamun, M., Hossain, M.: Feature extraction for hyperspectral image classification. In: 2017 IEEE Region 10 Humanitarian Technology Conference (R10-HTC), pp. 379–382. IEEE (2017)
Uddin, M.P., Mamun, M.A., Afjal, M.I., Hossain, M.A.: Information-theoretic feature selection with segmentation-based folded principal component analysis (pca) for hyperspectral image classification. Int. J. Remote Sens. 42(1), 286–321 (2020)
Uddin, M., Mamun, M., Hossain, M.: Segmented FPCA for hyperspectral image classification. In: 2017 3rd International Conference on Electrical Information and Communication Technology (EICT), pp. 1–6. IEEE (2017)
Mishu, S.Z., Ahmed, B., Hossain, M.A., Uddin, M.P.: Effective subspace detection based on the measurement of both the spectral and spatial information for hyperspectral image classification. Int. J. Remote Sens. 41(19), 7541–7564 (2020)
Mohan, B.K., Porwal, A.: Hyperspectral image processing and analysis. Curr. Sci. 108, 833–841 (2015)
Guo, B., Gunn, S.R., Damper, R.I., Nelson, J.D.: Band selection for hyperspectral image classification using mutual information. IEEE Geosci. Remote Sens. Lett. 3(4), 522–526 (2006)
Uddin, M.P., Mamun, M.A., Hossain, M.A., Afjal, M.I.: Improved folded-pca for efficient remote sensing hyperspectral image classification. In: Geocarto International (just-accepted), pp. 1–28 (2021)
Uddin, M., Mamun, M., Hossain, M.: Improved feature extraction using segmented fpca for hyperspectral image classification. In: 2017 2nd International Conference on Electrical & Electronic Engineering (ICEEE), pp. 1–4. IEEE (2017)
Uddin, M.P., Mamun, M.A., Hossain, M.A.: Pca-based feature reduction for hyperspectral remote sensing image classification. IETE Techn. Rev. 38(4), 377–396 (2021)
Jia, X., Kuo, B.C., Crawford, M.M.: Feature mining for hyperspectral image classification. Proc. IEEE 101(3), 676–697 (2013)
Melgani, F., Bruzzone, L.: Classification of hyperspectral remote sensing images with support vector machines. IEEE Trans. Geosci. Remote Sens. 42(8), 1778–1790 (2004)
Tsai, F., Lin, E.K., Yoshino, K.: Spectrally segmented principal component analysis of hyperspectral imagery for mapping invasive plant species. Int. J. Remote Sens. 28(5), 1023–1039 (2007)
Fauvel, M., Chanussot, J., Benediktsson, J.A.: Kernel principal component analysis for feature reduction in hyperspectrale images analysis. In: Proceedings of the 7th Nordic Signal Processing Symposium-NORSIG 2006, pp. 238–241. IEEE (2006)
Shao, Y., Sang, N., Gao, C., Ma, L.: Spatial and class structure regularized sparse representation graph for semi-supervised hyperspectral image classification. Pattern Recogn. 81, 81–94 (2018)
Liu, B., Yu, X., Zhang, P., Yu, A., Fu, Q., Wei, X.: Supervised deep feature extraction for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 56(4), 1909–1921 (2017)
Zhao, B., Ulfarsson, M.O., Sveinsson, J.R., Chanussot, J.: Unsupervised and supervised feature extraction methods for hyperspectral images based on mixtures of factor analyzers. Remote Sens. 12(7), 1179 (2020)
Xu, P.: Truncated SVD methods for discrete linear ill-posed problems. Geophys. J. Int. 135(2), 505–514 (1998)
Cao, L., Chua, K.S., Chong, W., Lee, H., Gu, Q.: A comparison of PCA, KPCA and ICA for dimensionality reduction in support vector machine. Neurocomputing 55(1–2), 321–336 (2003)
Rodarmel, C., Shan, J.: Principal component analysis for hyperspectral image classification. Surv. Land Inf. Sci. 62(2), 115–122 (2002)
Uddin, M.P., Mamun, M.A., Hossain, M.A.: Effective feature extraction through segmentation-based folded-pca for hyperspectral image classification. Int. J. Remote Sens. 40(18), 7190–7220 (2019)
Jia, X., Richards, J.A.: Segmented principal components transformation for efficient hyperspectral remote-sensing image display and classification. IEEE Trans. Geosci. Remote Sens. 37(1), 538–542 (1999)
Wall, M.E., Rechtsteiner, A., Rocha, L.M.: Singular value decomposition and principal component analysis. In: A Practical Approach to Microarray Data Analysis, pp. 91–109. Springer, Heidelberg (2003). https://doi.org/10.1007/0-306-47815-3_5
Hansen, P.C.: Truncated singular value decomposition solutions to discrete ill-posed problems with ill-determined numerical rank. SIAM J. Sci. Stat. Comput. 11(3), 503–518 (1990)
Baumgardner, M.F., Biehl, L.L., Landgrebe, D.A.: 220 band aviris hyperspectral image data set: June 12, 1992 indian pine test site 3. Purdue University Research Repository 10, R7RX991C (2015)
Tu, B., Zhou, C., He, D., Huang, S., Plaza, A.: Hyperspectral classification with noisy label detection via superpixel-to-pixel weighting distance. IEEE Trans. Geosci. Remote Sens. 58(6), 4116–4131 (2020)
Yan, Y., Ren, J., Tschannerl, J., Zhao, H., Harrison, B., Jack, F.: Nondestructive phenolic compounds measurement and origin discrimination of peated barley malt using near-infrared hyperspectral imagery and machine learning. IEEE Trans. Instrument. Meas. 70, 1–15 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Rahman, M.M., Ahmed, S., Haque, M.S., Marjan, M.A., Afjal, M.I., Uddin, M.P. (2023). Segmented-Truncated-SVD for Effective Feature Extraction in Hyperspectral Image Classification. In: Satu, M.S., Moni, M.A., Kaiser, M.S., Arefin, M.S. (eds) Machine Intelligence and Emerging Technologies. MIET 2022. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 491. Springer, Cham. https://doi.org/10.1007/978-3-031-34622-4_42
Download citation
DOI: https://doi.org/10.1007/978-3-031-34622-4_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-34621-7
Online ISBN: 978-3-031-34622-4
eBook Packages: Computer ScienceComputer Science (R0)