Skip to main content
Log in

Dimensionality Reduction of Hyperspectral Images Using Pooling

  • Representation, Processing, Analysis, and Understanding of Images
  • Published:
  • volume 29pages 72–78 (2019)
Pattern Recognition and Image Analysis Aims and scope

Cite this article


Hyperspectral image having huge numbers of narrow and contiguous bands involves high computation complexity in processing and analysing the image. Hence dimensionality reduction is applied as an essential pre-processing step for hyperspectral data. Pooling is a technique of reducing spatial dimension and successfully applied in convolutional neural network. There are various types of pooling strategies present viz. max pool, mean pool and having their respective merits. In the present article, the concept of pooling is applied in the spectral dimension of the hyperspectral data to reduce the dimensionality and compared the result with standard reduction process like principal component analysis. Different pooling methods are applied and compared across and the mean pooling is found to be performing better. The results are compared in terms of overall accuracy and execution time.

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

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions


  1. J. M. Yang, P. T. Yu, and B. C. Kuo, “A nonparametric feature extraction and its application to nearest neighbor classification for hyperspectral image data,” IEEE Trans. Geosci. Remote Sens. 48 (3), 1279–1293 (2010).

    Article  Google Scholar 

  2. D. S. Kim, M. W. Pyeon, Y. D. Eo, Y. G. Byun, and Y. Il Kim, “Automatic pseudo-invariant feature extraction for the relative radiometric normalization of Hyperion hyperspectral images.” GISci. Remote Sens. 49 (5), 755–773 (2012).

    Article  Google Scholar 

  3. K. Koonsanit, C. Jaruskulchai, and A. Eiumnoh. “Band selection for hyperspectral imagery with PCAMIG,” in Web-Age Information Management, Proc. WAIM 2012 International Workshops: GDMM, IWSN, MDSP, USDM, and XMLDM, Harbin, China, Aug. 2012, Ed. by Z. Bao, Y. Gao, et al., Lecture Notes in Computer Science (Springer, Berlin, Heidelberg, 2012), Vol. 7419, pp. 119–127.

    Google Scholar 

  4. M. Imani and H. Ghassemian, “Two dimensional linear discriminant analyses for hyperspectral data,” Photogram. Eng. Remote Sens. 81 (10), 777–786 (2015).

    Article  Google Scholar 

  5. R. Lazcano, D. Madroñal, R. Salvador, K. Desnos, M. Pelcat, R. Guerra, H. Fabelo, S. Ortega, S. López, G. Callicó, E. Juarez, and C. Sanz, “Porting a PCA-based hyperspectral image dimensionality reduction algorithm for brain cancer detection on a manycore architecture,” J. Syst. Archit. 77, 101–111 (2017).

    Article  Google Scholar 

  6. H. Yang, Q. Du, and G. Chen, “Unsupervised hyper-spectral band selection using graphics processing units,” IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 4 (3), 660–668 (2011).

    Article  Google Scholar 

  7. S. Jia, Z. Ji, and L. Shen, “Unsupervised band selection for hyperspectral imagery classification without manual band removal,” IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 5 (2), 531–543 (2012).

    Article  Google Scholar 

  8. K. Tan, E. Li, Q. Du, and P. Du, “Hyperspectral image classification using band selection and morphological profiles,” IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 7 (1), 40–48 (2014).

    Article  Google Scholar 

  9. S. Li, J. Qiu, X. Yang, H. Liu, D. Wan, and Y. Zhu, “A novel approach to hyperspectral band selection based on spectral shape similarity analysis and fast branch and bound search,” Eng. Appl. Artif. Intell. 27, 241–250 (2014).

    Article  Google Scholar 

  10. A. Paul, S. Bhattacharya, D. Dutta, J. R. Sharma, and V. K. Dadhwal, “Band selection in hyperspectral imagery using spatial cluster mean and genetic algorithms,” GISci. Remote Sens. 52 (6), 644–661 (2015). doi:

    Article  Google Scholar 

  11. H. Su, Y. Cai, and Q. Du, “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 (2016).

    Article  Google Scholar 

  12. R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification, 2nd ed. (Wiley, New York, 2012).

    MATH  Google Scholar 

  13. F. Luo, H. Huang, Z. Ma, and J. Liu, “Semisupervised sparse manifold discriminative analysis for feature extraction of hyperspectral images,” IEEE Trans. Geosci. Remote Sens. 54 (10), 6197–6211 (2016). doi:

    Article  Google Scholar 

  14. H. Yang, Q. Du, H. Su, and Y. Sheng, “An efficient method for supervised hyperspectral band selection,” IEEE Geosci. Remote Sens. Lett. 8 (1), 138–142 (2011).

    Article  Google Scholar 

  15. C. Sui, Y. Tian, Y. Xu, and Y. Xie, “Unsupervised band selection by integrating the overall accuracy and redundancy,” IEEE Geosci. Remote Sens. Lett. 12 (1), 185–189 (2015).

    Article  Google Scholar 

  16. J. Yin, Y. Wang, and J. Hu, “A new dimensionality reduction algorithm for hyperspectral image using evolutionary strategy,” IEEE Trans. Ind. Inf. 8 (4), 935–943 (2011).

    Article  Google Scholar 

  17. S. Li, H. Wu, D. Wan, and J. Zhu, “An effective feature selection method for hyperspectral image classification based on genetic algorithm and support vector machine,” Knowl.-Based Syst. 24 (1), 40–48 (2011).

    Article  Google Scholar 

  18. H. Yang, Q. Du, and G. Chen, “Particle swarm optimization-based hyperspectral dimensionality reduction for urban land cover classification,” IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 5 (2), 544–554 (2012).

    Article  Google Scholar 

  19. H. Su, Q. Du, G. Chen, and P. Du, “Optimized hyper-spectral band selection using particle swarm optimization”, IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 7 (6), 2659–2670 (2014).

    Article  Google Scholar 

  20. P. Ghamisi and J. A. Benediktsson, “Feature selection based on hybridization of genetic algorithm and particle swarm optimization,” IEEE Geosci. Remote Sens. Lett. 12 (2), 309–313 (2015). doi:

    Article  Google Scholar 

  21. X. Cao, J. Han, S. Yang, D. Tao, and L. Jiao, “Band selection and evaluation with spatial information,” Int. J. Remote Sens. 37 (19), 4501–4520 (2016). doi:.

    Article  Google Scholar 

  22. D. Erhan, C. Szegedy, A. Toshev, and D. Anguelov, “Scalable object detection using deep neural networks,” in Proc. 2014 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR 2014) (Columbus, OH, 2014), pp. 2155–2162.

    Chapter  Google Scholar 

  23. A. Adrian, K. Jasleen, and M. Gonzalez, “Using convolutional networks and satellite imagery to identify patterns in urban environments at a large scale,” arXiv preprint arXiv:1704.02965 (2017).

  24. X. X. Zhu, D. Tuia, L. Mou, G.-S. Xia, L. Zhang, F. Xu, and F. Fraundorfer, “Deep learning in remote sensing: A comprehensive review and list of resources,” IEEE Geosci. Remote Sens. Mag. 5 (4), 8–36 (2017).

    Article  Google Scholar 

  25. K. Makantasis, K. Karantzalos, A. Doulamis, and N. Doulamis, “Deep supervised learning for hyperspectral data classification through convolutional neural networks,” in Proc. 2015 IEEE Int. Geoscience and Remote Sensing Symposium (IGARSS) (Milan, Italy, 2015), pp. 4959–4962.

    Chapter  Google Scholar 

  26. W. Hu, Y. Huang, L. Wei, F. Zhang, and H. Li, “Deep convolutional neural networks for hyperspectral image classification,” J. Sens. 2015, Article ID 258619, 12 pages (2015).

  27. W. Zhao and S. Du, “Spectral-spatial feature extraction for hyperspectral image classification: A dimension reduction and deep learning approach,” IEEE Trans. Geosci. Remote Sens. 54 (8), 4544–4554 (2016).

    Article  Google Scholar 

  28. P. Ghamisi, Y. Chen, and X. Zhu, “A self-improving convolution neural network for the classification of hyperspectral data,” IEEE Geosci. Remote Sens. Lett. 13 (10), 1537–1541 (2016).

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations


Corresponding author

Correspondence to Arati Paul.

Additional information

The article is published in the original.

Arati Paul is a Scientist in Regional Remote Sensing Centre – East, National Remote Sensing Centre, Indian Space Research Organisation. She has completed B.Tech., followed by M.Tech. in computer science and Engineering. Her area of work includes remote sensing, GIS, image processing and data analytics. She has published nearly 40 research papers and technical reports in her area of expertise.

Nabendu Chaki is a Professor in the Department Computer Science and Engineering, University of Calcutta, Kolkata, India. He is sharing 7 international patents including 4 US patents. Besides editing more than 30 conference proceedings with Springer, Dr. Chaki has authored 7 text and research books and nearly 200 Scopus Indexed research papers in Journals and International conferences. He has served as a Visiting Professor in different places including Naval Postgraduate School, USA; Ca Foscari University, Italy and AGH University in Poland. He is the founder Chair of ACM Professional Chapter in Kolkata and served in that capacity for 3 years since January 2014. He was active during 2009–2015 towards developing several international standards in Software Engineering and Service Science as a Global (GD) member for ISO-IEC.

Rights and permissions

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Paul, A., Chaki, N. Dimensionality Reduction of Hyperspectral Images Using Pooling. Pattern Recognit. Image Anal. 29, 72–78 (2019).

Download citation

  • Received:

  • Published:

  • Issue Date:

  • DOI: