Skip to main content
SpringerLink
Log in

Spectral���Spatial Feature Reduction for Hyperspectral Image Classification

  • Conference paper
  • First Online:
Machine Intelligence and Emerging Technologies (MIET 2022)

Abstract

Hyperspectral Image (HSI) has many narrow and continuous spectral bands. There are many problems with the original HSI. For example, the classification accuracy of the test data is affected by the curse of dimensionality problem because the image bands are highly correlated in both space and time. So, dimensionality reduction is done and improved the classification result. In this paper, a deep convolutional network is suggested to reduce the dimensionality of HSI classification by considering both spectral and spatial features. When combined factor analysis and mRMR are used, spectral features are reduced, while 2D wavelet CNN reduces spatial features. A wavelet CNN is an extension of a 2D CNN that can be used to classify high-resolution images. Wavelet CNNs also use layered wavelet transformations to pull out spectral features. A wavelet CNN is easier to calculate than a 3D CNN or a 2D-3D CNN. In the next step, the spectral features are connected to the two-dimensional CNN to get the spatial features, creating a spatial-spectral feature vector. It makes a model that can accurately classify HSI data at multiple resolutions. As part of the HSI classification, we used data sets from the Pavia University and Salinas Scene dataset to see how well the two methods work together. In two datasets, the proposed Expanded 2DNET did better than the handcrafted methods, according to the experiment.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
eBook
USD 109.00
Price excludes VAT (USA)
Softcover Book
USD 139.99
Price excludes VAT (USA)

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Chen, Z., Jiang, J., Jiang, X., Fang, X., Cai, Z.: Spectral-spatial feature extraction of hyperspectral images based on propagation filter. Sensors 18, 1978 (2018). https://doi.org/10.3390/s18061978

    Article  Google Scholar 

  2. Kong, Y., Wang, X., Cheng, Y.: Spectral–spatial feature extraction for HSI classification based on supervised hypergraph and sample expanded CNN. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 11, 4128–4140 (2018). https://doi.org/10.1109/JSTARS.2018.2869210

    Article  Google Scholar 

  3. Zhao, W., Du, S.: Spectral-spatial feature extraction for hyperspectral image classification: a dimension reduction and deep learning approach. IEEE Trans. Geosci. Remote Sens. 54, 4544–4554 (2016). https://doi.org/10.1109/TGRS.2016.2543748

    Article  Google Scholar 

  4. Ali, M.U., Ahmed, S., Ferzund, J., Mehmood, A., Rehman, A.: Using PCA and factor analysis for dimensionality reduction of bio-informatics data. Int. J. Adv. Comput. Sci. Appl. (2017). https://doi.org/10.48550/arXiv.1707.07189

  5. Islam, R., Ahmed, B., Hossain, M.A.: Feature reduction based on segmented principal component analysis for hyperspectral images classification (2019). https://doi.org/10.1109/ECACE.2019.8679394

  6. Salas-Gonzalez, D., et al.: Feature selection using factor analysis for Alzheimer’s diagnosis using 18F-FDG PET images. Med. Phys. 37, 6084–6095 (2010)

    Article  Google Scholar 

  7. Islam, R., Ahmed, B., Hossain, M.A.: Feature reduction of hyperspectral image for classification. Spatial Science (2020). https://doi.org/10.1080/14498596.2020.1770137

  8. Xu, Y., Jones, G., Li, J., Wang, B., Sun, C.: A study on mutual information-based feature selection for text categorization. J. Comput. Inf. Syst. 3, 1007–1012 (2007)

    Google Scholar 

  9. Diakite, A., Gui, J., Xiaping, F.: Hyperspectral image classification using 3D 2D CNN. IET Image Proc. 15 (2021). https://doi.org/10.1049/ipr2.12087

  10. Roy, S., Krishna, G., Dubey, S.R., Chaudhuri, B.: HybridSN: exploring 3-D-2-D CNN feature hierarchy for hyperspectral image classification. IEEE Geosci. Remote Sens. Lett. 17, 277–281 (2019). https://doi.org/10.1109/LGRS.2019.2918719

    Article  Google Scholar 

  11. Chakraborty, T., Trehan, U.: SpectralNET: exploring spatial-spectral waveletCNN for hyperspectral image classification (2021). Arxiv preprint Arxiv:2104.00341

    Google Scholar 

  12. Khosla, N.: Dimensionality reduction using factor analysis. Griffith University, Australia (2004)

    Google Scholar 

  13. Shrestha, N.: Factor analysis as a tool for survey analysis. Am. J. Appl. Math. Stat. 9(1), 4–11 (2021). https://doi.org/10.12691/ajams-9-1-2

    Article  MathSciNet  Google Scholar 

  14. Shu, W., Qian, W.: Mutual information-based feature selection from set-valued data, pp. 733–739 (2014). https://doi.org/10.1109/ICTAI.2014.114

  15. Zhou, H., Wang, X., Zhu, R.: Feature selection based on mutual information with correlation coefficient. Appl. Intell. 52(5), 5457–5474 (2021). https://doi.org/10.1007/s10489-021-02524-x

    Article  Google Scholar 

  16. Vergara, J.R., Estévez, P.A.: A review of feature selection methods based on mutual information. Neural Comput. Appl. 24(1), 175–186 (2013). https://doi.org/10.1007/s00521-013-1368-0

    Article  Google Scholar 

  17. De Jay, N., Papillon-Cavanagh, S., Olsen, C., El-Hachem, N., Bontempi, G., Haibe-Kains, B.: mRMRe: an R package for parallelized mRMR ensemble feature selection. Bioinformatics 29(18), 2365–2368 (2013)

    Article  Google Scholar 

  18. Kursun, O., Sakar, C.O., Favorov, O., Aydin, N., Gurgen, F.: Using covariates for improving the minimum redundancy maximum relevance feature selection method. Turk. J. Electr. Eng. Comput. Sci. 18, 975–987 (2010). https://doi.org/10.3906/elk-0906-75

    Article  Google Scholar 

  19. Aghaeipoor, F., Javidi, M.M.: A hybrid fuzzy feature selection algorithm for high-dimensional regression problems: an mRMR-based framework. Expert Syst. Appl. 162, 113859 (2020). https://doi.org/10.1016/j.eswa.2020.113859

    Article  Google Scholar 

  20. Billah, M., Waheed, S.: Minimum redundancy maximum relevance (mRMR) based feature selection from endoscopic images for automatic gastrointestinal polyp detection. Multimedia Tools and Applications 79(33–34), 23633–23643 (2020). https://doi.org/10.1007/s11042-020-09151-7

    Article  Google Scholar 

  21. Vaddi, R., Manoharan, P.: Probabilistic PCA based hyper spectral image classification for remote sensing applications. In: Abraham, A., Cherukuri, A.K., Melin, P., Gandhi, N. (eds.) ISDA 2018 2018. AISC, vol. 941, pp. 863–869. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-16660-1_84

    Chapter  Google Scholar 

  22. Vaddi, R., Prabukumar, M.: Hyperspectral image classification using CNN with spectral and spatial features integration. Infrared Phys. Technol. 107, 103296 (2020). https://doi.org/10.1016/j.infrared.2020.103296

    Article  Google Scholar 

  23. Wang, K., Cheng, L., Yong, B.: Spectral-similarity-based kernel of SVM for hyperspectral image classification. Remote Sens. 12, 2154 (2020). https://doi.org/10.3390/rs12132154

    Article  Google Scholar 

  24. Aparna, G., Rachana, K., Rikhita, K., Phaneendra Kumar, B.L.N.: Comparison of feature reduction techniques for change detection in remote sensing. In: Chowdary, P.S.R., Anguera, J., Satapathy, S.C., Bhateja, V. (eds.) Evolution in Signal Processing and Telecommunication Networks. LNEE, vol. 839, pp. 325–333. Springer, Singapore (2022). https://doi.org/10.1007/978-981-16-8554-5_30

    Chapter  Google Scholar 

  25. Kong, F., Hu, K., Li, Y., Li, D., Zhao, S.: Spectral-spatial feature partitioned extraction based on CNN for multispectral image compression. Remote Sens. 13, 9 (2020). https://doi.org/10.3390/rs13010009

    Article  Google Scholar 

  26. Fujieda, S., Takayama, K., Hachisuka, T.: Wavelet convolutional neural networks (2018). arXiv preprint arXiv:1805.08620

  27. Ghaderizadeh, S., Abbasi-Moghadam, D., Sharifi, A., Zhao, Na., Tariq, A.: Hyperspectral image classification using a hybrid 3D-2D convolutional neural networks. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 14, 7570–7588 (2021). https://doi.org/10.1109/JSTARS.2021.3099118

    Article  Google Scholar 

  28. Wang, C., Ma, N., Ming, Y., Wang, Q., Xia, J.: Classification of hyperspectral imagery with a 3D convolutional neural network and J-M distance. Adv. Space Res. 64, 886–899 (2019). https://doi.org/10.1016/j.asr.2019.05.005

    Article  Google Scholar 

  29. Li, X., et al.: A wavelet transform-assisted convolutional neural network multi-model framework for monitoring large-scale fluorochemical engineering processes. Processes 8(11), 1480 (2020). https://doi.org/10.3390/pr8111480

    Article  Google Scholar 

  30. 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, 286–321 (2020). https://doi.org/10.1080/01431161.2020.1807650

    Article  Google Scholar 

  31. Fu, H., Sun, G., Jaime, Z., Aizhu, Z., Ren, J., Jia, X.: A novel spectral-spatial singular spectrum analysis technique for near real-time in situ feature extraction in hyperspectral imaging. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 13, 2214–2225 (2020). https://doi.org/10.1109/JSTARS.2020.2992230

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Computer Science and Engineering, Hajee Mohammad Danesh Science and Technology University, Dinajpur, Bangladesh

    Md. Touhid Islam, Mohadeb Kumar & Md. Rashedul Islam

Authors
  1. Md. Touhid Islam
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mohadeb Kumar
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Md. Rashedul Islam
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Md. Rashedul Islam .

Editor information

Editors and Affiliations

  1. Noakhali Science and Technology University, Noakhali, Bangladesh

    Md. Shahriare Satu

  2. The University of Queensland, St. Lucia, QLD, Australia

    Mohammad Ali Moni

  3. Jahangirnagar University, Dhaka, Bangladesh

    M. Shamim Kaiser

  4. Daffodil International University, Dhaka, Bangladesh

    Mohammad Shamsul Arefin

Rights and permissions

Reprints and permissions

Copyright information

© 2023 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Islam, M.T., Kumar, M., Islam, M.R. (2023). Spectral–Spatial Feature Reduction for 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_45

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-34622-4_45

  • 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)

Publish with us

Policies and ethics

Search

Navigation