Skip to main content
SpringerLink
Log in

Compression and classification methods for hyperspectral images

  • Image Processing, Analysis, Recognition, and Understanding
  • Published:
  • volume 16, pages 413–424 (2006)
Pattern Recognition and Image Analysis Aims and scope

Cite this article

Abstract

In this article we present new lossless compression methods by combining existing methods and compare them using AVIRIS images. These methods include the Self-Organizing Map (SOM), Principal Component Analysis (PCA), and the three-dimensional Wavelet Transform combined with traditional lossless encoding methods. The two-dimensional JPEG2000 and SPIHT compression methods were applied to the eigenimages produced by the PCA. The bit allocation for the compression of eigenimages was based on the amount of information in each eigenimage. In bit rate calculation we used the exponential entropy formula, which gave better results than the original linear version. The information loss from the compression was measured by the Signal-to-Noise Ratio (SNR) and Peak-Signal-to-Noise Ratio (PSNR). To get more illustrative and practical error measures, classification of spectra was performed using unsupervised K-means clustering combined with spectral matching. Spectral matching methods include Euclidean distance, Spectral Similarity Value (SSV), and Spectral Angle Mapper (SAM). We used two test images, which both were AVIRIS images with 224 bands and 512 lines in 614 columns. The PCA in the spectral dimension combined with JPEG2000 or SPIHT in the spatial dimension was the best method in terms of the image quality and compression speed.

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

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Institutional subscriptions

References

  1. P. Toivanen, A. Lehtinen, J. Ansamaki, and H. Kalviainen, “Two-Stage Multispectral Image Compression Using the Self-Organizing Map,” in Proceedings of the 11th Scandinavian Conference on Image Analysis SCIA’ 99, 1999.

  2. S. Lim, K. Sohn, and C. Lee, “Principal Component Analysis for Compression of Hyperspectral Images,” in Proceedings of IEEE geoscience and Remote Sensing Symposium, 2001 (IGARSS’ 01. IEEE 2001 International, 2001), pp. 97–99.

  3. P. L. Dragotti, G. Poggi, and R. P. Ragozini, “Compression of Hyperspectral Images by Three-Dimensional SPIHT Algorithm,” IEEE Trans. on Geoscience and Remote Sensing 38, 416–428 (2000).

    Article  Google Scholar 

  4. A. Kaarna and J. Parkkinen, “Transform Based Lossy Compression of Multipectral Images,” Pattern Analysis and Applications 4, 39–50 (2001).

    Article  MATH  MathSciNet  Google Scholar 

  5. J. Ziv and A. Lempel, “Compression of Individual Sequences via Variable Rate Coding,” IEEE Trans. on Information Theory IT-24, 530–536 (1978).

    Article  MathSciNet  Google Scholar 

  6. M. Nelson, “Data Compression with the Burrows-Wheeler Transform,” Dr. Dobb’s Journal (1996). Online. Available: http://dogma.net/markn/articles/bwt/bwt.htm.

  7. R. C. Gonzalez and R. E. Woods, Digital Image Processing (Prentice Hall, 2002), pp. 441–444.

  8. M. Rabbani and P. W. Jones, Digital Image Compression Techniques (SPIE, 1991).

  9. J.-S. R. Jang, C.-T. Sun, and E. Mizutani, Neuro-Fuzzy and Soft Computing, a Computational Approach to Learning and Machine Intelligence (Prentice Hall, 1997), pp. 424–425.

  10. J. C. Granahan and J. N. Sweet, “An Evaluation Of Atmospheric Correction Techniques Using The Spectral Similarity Scale,” in Proceedings of IEEE 2001 International Geoscience and Remote Sensing Symposium, Vol. 5, 2001, pp. 2022–2024.

    Google Scholar 

  11. C. I. Chang, “An Information-Theoretic Approach to Spectral Variability, Similarity, and Discrimination for Hyperspectral Image Analysis,” IEEE Trans on Information Theory 46, 1927–1932 (2000).

    Article  MATH  Google Scholar 

  12. C. E. Shannon, “A Mathematical Theory of Communication,” The Bell Sys. Tech. J. XXVII(2), 379–423 (1948).

    MathSciNet  Google Scholar 

  13. A. Said and W. A. Pearlman, “A New, Fast, and Efficient Image Codes Based on Set Partitioning in Hierarchical Trees,” IEEE Trans. on Circuits and Systems for Video Technology 6, pp. 234–250 (1996).

    Article  Google Scholar 

  14. SOM Toolbox home. Available: http://www.cis.hut.fi/projects/somtoolbox/, 2000.

  15. The bzip2 and libbzip2 home page. Available: http://sources.redhat.com/bzip2/, 2002.

  16. JPEG2000 Software: Kakadu. Available: http://www.kakadusoftware.com/, 2002.

  17. SPIHT image compression. Available: http://www.cipr.rpi.edu/research/SPIHT/, 2002.

  18. M. D. Pal, C. M. Brislawn, and S. P. Brumby, “Feature Extraction from Hyperspectral Images Compressed Using the JPEG-2000 Standard,” in Proceedings of Fifth IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI’02), 2002, pp. 168–172.

  19. J. M. Shapiro, “Embedded Image Coding Using Zerotrees of Wavelet Coefficients,” IEEE Trans. on Signal Processing 41, pp. 3445–3462 (1993).

    Article  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Information Technology, Lappeenranta University of Technology, P.O. Box 20, FIN-53851, Lappeenranta, Finland

    A. Kaarna & P. Keränen

  2. Digital Media Institute/EPANET/UCS, Tampere University of Technology, Frami, 60320, Seinäjoki, Finland

    P. Toivanen

Authors
  1. A. Kaarna
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. P. Toivanen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. P. Keränen
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

The text was submitted by the authors in English.

Arto Kaarna. Received MS (Mech. Eng.) degree in 1980, LicTech degree in 1990, and PhD (Tech.) in 2000 in computer science at Lappeenranta University of Technology, Finland (LUT). Currently working as a professor in media in networks with LUT. His main research interest is in color and spectral image processing.

Pekka Toivanen. Professor in Information Technology, graduated from Helsinki University of Technology in 1989. Worked at Nokia Electronics and Nokia Information Systems. In 1988–1991, worked at the Technical Research Centre of Finland as a researcher. Since 1991, working in the Department of Information Technology at the Lappeenranta University of Technology (LUT). Received PhD (Tech.) in 1996. Worked as an acting associate professor and professor in 1997–1999. In 2000, was on a one-year research visit to Linköping University/Campus Norrköpping, Sweden. Nominated as a professor in 2001 to Lappeenranta University of Technology. Head of the Laboratory of Information Processing at LUT. Member of SPIE and IEEE. Eleven international journal articles and 51 international conference publications. His main research interests are hyper-and multispectral image analysis, color, and distance transforms.

Pekka Keränen. Master of Science student and research assistant in the Department of Information Technology at the Lappeenranta University of Technology, Finland (LUT). Currently doing research in hyperspectral image compression and hyperspectral image quality measuring.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Kaarna, A., Toivanen, P. & Keränen, P. Compression and classification methods for hyperspectral images. Pattern Recognit. Image Anal. 16, 413–424 (2006). https://doi.org/10.1134/S1054661806030114

Download citation

  • Received:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S1054661806030114

Keywords

search

Navigation