Skip to main content
SpringerLink
Log in

Feature Extraction Techniques for Hyperspectral Images Classification

  • Conference paper
  • First Online:
Soft Computing Applications (SOFA 2018)

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 1222))

Included in the following conference series:

Abstract

Recently, several feature extraction techniques have been exploited to resolve the hyperspectral dimension reduction issue. Feature extraction methods can be widely categorized as either linear or nonlinear methods. In this paper, we are interested to present and assess the two families’ yields, during hyperspectral classification tasks. We empirically compare the most popular feature extraction approaches based on classification accuracies and speed output. The tests are performed on two real hyperspectral images (HSIs). Experiment results show that nonlinear techniques provide better classification results compared to linear methods. However, linear approaches require less computing load.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 169.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 219.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Laparra, V., Malo, J., Camps-Valls, G.: Dimensionality reduction via regression in hyperspectral imagery. IEEE J. Sel. Top. Sign. Process. 9(6), 1026–1036 (2015)

    Google Scholar 

  2. Kurz, T.H., Buckley, S.J.: A review of hyperspectral imaging in close range applications. In: The International Society for Photogrammetry and Remote Sensing Congress, pp. 865–870. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Prague, Czech Republic (2016)

    Google Scholar 

  3. Computational Intelligence search group site. http://www.ehu.eus/ccwintco/index.php?title=Hyperspectral_Remote_Sensing_Scenes. Accessed 05 Dec 2017

  4. Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 1–27 (2011)

    Google Scholar 

  5. Ma, L., Crawford, M.M., Tian, J.: Anomaly detection for hyperspectral images using local tangent space alignment. In: 2010 IEEE International Geoscience and Remote Sensing Symposium, Honolulu, HI, USA, pp. 824–827. IEEE (2010)

    Google Scholar 

  6. Ma, L., Crawford, M.M., Tian, J.W.: Generalised supervised local tangent space alignment for hyperspectral image classification. Electron. Lett. 46(7), 497–498 (2010)

    Google Scholar 

  7. Huang, H., Yang, M.: Dimensionality reduction of hyperspectral images with sparse discriminant embedding. IEEE Trans. Geosci. Remote Sens. 53(9), 5160–5169 (2015)

    Google Scholar 

  8. Khodr, J., Younes, R.: Dimensionality reduction on hyperspectral images: a comparative review based on artificial datas. In: 2011 4th International Congress on Image and Signal Processing, Shanghai, China, pp. 1875–1883. IEEE (2011)

    Google Scholar 

  9. Khoder, J.: Nouvel Algorithme pour la Réduction de la Dimensionnalité en Imagerie Hyperspectrale. Ph.D. thesis, the University of Versailles St Quentin-en-Yvelines and the Lebanese University (2014)

    Google Scholar 

  10. Donoho, D.L., Grimes, C.: Hessian eigenmaps: new locally linear embedding techniques for high-dimensional data. Nat. Acad. Sci. 100(10), 5591–5596 (2013)

    MATH  Google Scholar 

  11. Lodha, S.P., Kamlapur, S.M.: Dimensionality reduction techniques for hyperspectral images. Int. J. Appl. Innov. Eng. Manage. (IJAIEM) 3(10), 92–99 (2014)

    Google Scholar 

  12. Lu, G., Fei, B.: Medical hyperspectral imaging: a review. J. Biomed. Opt. 19(1), 1–23 (2014)

    Google Scholar 

  13. Zhang, L., Zhang, L., Tao, D., Huang, X.: Tensor discriminative locality alignment for hyperspectral image spectral-spatial feature extraction. IEEE Trans. Geosci. Remote Sens. 51(1), 242–256 (2013)

    Google Scholar 

  14. Ren, J., Zabalza, J., Marshall, S., Zheng, J.: Effective feature extraction and data reduction in remote sensing using hyperspectral imaging [applications corner]. IEEE Signal Process. Mag. 31(4), 149–154 (2014)

    Google Scholar 

  15. Deepa, P., Thilagavathi, K.: Feature extraction of hyperspectral image using principal component analysis and folded-principal component analysis. In: 2015 2nd International Conference on Electronics and Communication System (ICECS), Coimbatore, India, pp. 656–660. IEEE (2015)

    Google Scholar 

  16. Luo, H., Tang, Y.Y., Li, C., Yang, L.: Local and global geometric structure preserving and application to hyperspectral image classification. Math. Probl. Eng. 2015, 13 (2015)

    Google Scholar 

  17. Zhai, Y., Zhang, L., Wang, N., Guo, Y., Cen, Y., Wu, T., Tong, Q.: A modified locality-preserving projection approach for hyperspectral image classification. IEEE Geosci. Remote Sens. Lett. 13(8), 1059–1063 (2016)

    Google Scholar 

  18. Zhang, X., Chew, S.E., Xu, Z., Cahill, N.D.: SLIC superpixels for efficient graph-based dimensionality reduction of hyperspectral imagery. In: SPIE Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XXI, p. 947209 (2015)

    Google Scholar 

  19. France, S.L., Carroll, J.D.: Two-way multidimensional scaling: a review. IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.) 41(5), 644–661 (2011)

    Google Scholar 

  20. Long, Y., Li, H.-C., Celik, T., Longbotham, N., Emery, W.J.: Pairwise-distance-analysis- driven dimensionality reduction model with double mappings for hyperspectral image visualization. Remote Sens. 7(6), 7785–7808 (2015)

    Google Scholar 

  21. Fang, J., Qian, Y.: Local detail enhanced hyperspectral image visualization. In: 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Milan, Italy, pp. 1092–1095. IEEE (2015)

    Google Scholar 

  22. Naud, A., Duch, W.: Visualization of large data sets using MDS combined with LVQ. In: The 6th International Conference on Neural Networks and Soft Computing, Zakopane, Poland, pp. 632–637 (2002)

    Google Scholar 

  23. De Silva, V., Tenenbaum, J.B.: Global versus local methods in nonlinear dimensionality reduction. In: The 15th International Conference on Neural Information Processing Systems, MA, USA, pp. 721–728 (2003)

    Google Scholar 

  24. Velasco-Forero, S., Angulo, J., Chanussot, J.: Morphological image distances for hyperspectral dimensionality exploration using Kernel-PCA and ISOMAP. In: 2009 IEEE International Geoscience and Remote Sensing Symposium, The Cape, South Africa, pp. III-109–III-112. IEEE (2009)

    Google Scholar 

  25. Jin, C., Bachmann, C.M.: Parallel acceleration of ISOMAP algorithm applied in hyperspectral imagery using OpenCL on heterogeneous systems. In: The 35th Canadian Symposium on Remote Sensing (2014)

    Google Scholar 

  26. Sun, W., Halevy, A., Benedetto, J.J., Czaja, W., Liu, C., Wu, H., Shi, B., Li, W.: UL-ISOMAP based nonlinear dimensionality reduction for hyperspectral imagery classification. ISPRS J. Photogramm. Remote Sens. 89, 25–36 (2014)

    Google Scholar 

  27. Du Plessis, L., Xu, R., Damelin, S., Sears, M., Wunsch, D.C.: Reducing dimensionality of hyperspectral data with diffusion maps and clustering with k-means and Fuzzy ART. Int. J. Syst. Control Commun. 3(3), 232–251 (2011)

    Google Scholar 

  28. Xu, R., Du Plessis, L., Damelin, S., Sears, M., Wunsch, D.C.: Analysis of hyperspectral data with diffusion maps and fuzzy ART. In: 2009 International Joint Conference on Neural Networks, Atlanta, GA, USA, pp. 3390–3397. IEEE (2009)

    Google Scholar 

  29. Licciardi, G.A., Chanussot, J., Vasile, G., Piscini, A.: Enhancing hyperspectral image quality using nonlinear PCA. In: 2014 IEEE International Conference on Image Processing (ICIP), Paris, France, pp. 5087–5091, IEEE (2014)

    Google Scholar 

  30. Liao, W., Pizurica, A., Philips, W., Pi, Y.: A fast iterative kernel PCA feature extraction for hyperspectral images. In: 2010 17th IEEE International Conference on Image Processing (ICIP), Hong Kong, China, pp. 1317–1320. IEEE (2010)

    Google Scholar 

  31. Ghedira, H.: Utilisation de réseaux de Neurones pour la cartographie des milieux humides à partir d’une Séries temporelle d’image RADARSAT-1. Ph.D. thesis, University of Quebec INRS-Eau, August 2002

    Google Scholar 

  32. Xing, C., Ma, L., Yang, X.: Stacked denoise autoencoder based feature extraction and classification for hyperspectral images. J. Sens. 2016, 10 (2016)

    Google Scholar 

  33. Wadstromer, N., Gustafsson, D.: Non-linear hyperspectral subspace mapping using stacked autoencoder. In: The 29th Annual Workshop of the Swedish Artificial Intelligence Society (SAIS), Malmö, Sweden (2016)

    Google Scholar 

  34. Ma, L., Crawford, M.M., Tian, J.: Anomaly detection for hyperspectral images based on robust locally linear embedding. J. Infrared Millim. Te. Waves 31(6), 753–762 (2010)

    Google Scholar 

  35. Zhang, L., Zhao, C.: Sparsity divergence index based on locally linear embedding for hyperspectral anomaly detection. J. Appl. Remote Sens. 10(2), 025026 (2016)

    Google Scholar 

  36. Chen, G., Qian, S.-E.: Dimensionality reduction of hyperspectral imagery using improved locally linear embedding. J. Appl. Remote Sens. 1(1), 1–10 (2007)

    MathSciNet  Google Scholar 

  37. Kang, X., Li, S., Fang, L., Benediktsson, J.A.: Intrinsic image decomposition for feature extraction of hyperspectral images. IEEE Trans. Geosci. Remote Sens. 53(4), 2241–2253 (2015)

    Google Scholar 

  38. Wang, J.: Hessian Locally Linear Embedding. In: Geometric Structure of High-Dimensional Data and Dimensionality Reduction, pp. 249–265. Springer, Heidelberg (2011)

    Google Scholar 

  39. Fejjari, A., Saheb Ettabaa, K., Korbaa, O.: Modified Schroedinger eigenmap projections algorithm for hyperspectral imagery classification. In: IEEE/ACS 14th International Conference on Computer Systems and Applications (AICCSA), Hamammet, Tunisia, pp. 809–814. IEEE (2017)

    Google Scholar 

  40. Fejjari, A., Saheb Ettabaa, K., Korbaa, O.: Modified graph-based algorithm for efficient hyperspectral feature extraction. In: the 32nd International Symposium on Computer and Information Sciences (ISCIS), Poznan, Poland, pp. 87–95. Springer (2018)

    Google Scholar 

  41. Fejjari, A., Saheb Ettabaa, K., Korbaa, O.: Fast spatial spectral Schroedinger eigenmaps algorithm for hyperspectral feature extraction. In: the 22nd International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES), Belgrade, Serbia, pp. 656–664 (2018)

    Google Scholar 

Download references

Acknowledgment

This work was supported and financed by the Ministry of Higher Education and Scientific Research of Tunisia.

Author information

Authors and Affiliations

  1. MARS (Modeling of Automated Reasoning Systems) Research Laboratory, ISITCom, University of Sousse, 4011, Hammam Sousse, Tunisia

    Asma Fejjari & Ouajdi Korbaa

  2. IMT Atlantique, ITI Department, Telecom Bretagne, 655 Street of Technopôle, 29200, Plouzané, France

    Karim Saheb Ettabaa

Authors
  1. Asma Fejjari
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Karim Saheb Ettabaa
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ouajdi Korbaa
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Asma Fejjari .

Editor information

Editors and Affiliations

  1. "Aurel Vlaicu" University of Arad, Faculty of Engineering, Arad, Romania

    Valentina Emilia Balas

  2. Faculty of Engineering and Information Technology, University of Technology Sydney, Centre for Artificial Intelligence, Sydney, Australia

    Lakhmi C. Jain

  3. Faculty of Engineering, “Aurel Vlaicu” University of Arad, Arad, Arad, Romania

    Marius Mircea Balas

  4. Department of Information Technology and Programming, Azerbaijan Technical University, Baku, Azerbaijan

    Shahnaz N. Shahbazova

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Fejjari, A., Saheb Ettabaa, K., Korbaa, O. (2021). Feature Extraction Techniques for Hyperspectral Images Classification. In: Balas, V., Jain, L., Balas, M., Shahbazova, S. (eds) Soft Computing Applications. SOFA 2018. Advances in Intelligent Systems and Computing, vol 1222. Springer, Cham. https://doi.org/10.1007/978-3-030-52190-5_12

Download citation

Publish with us

Policies and ethics

Search

Navigation