Skip to main content
Springer Nature Link
Log in

Generating labeled samples for hyperspectral image classification using correlation of spectral bands

  • Research Article
  • Published:
Frontiers of Computer Science Aims and scope Submit manuscript

Abstract

Because the labor needed to manually label a huge training sample set is usually not available, the problem of hyperspectral image classification often suffers from a lack of labeled training samples. At the same time, hyperspectral data represented in a large number of bands are usually highly correlated. In this paper, to overcome the small sample problem in hyperspectral image classification, correlation of spectral bands is fully utilized to generate multiple new sub-samples from each original sample. The number of labeled training samples is thus increased several times. Experiment results demonstrate that the proposed method has an obvious advantage when the number of labeled samples is small.

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

Access this article

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

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

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Zhong Y, Zhang L. An adaptive artificial immune network for supervised classification of multi-hyperspectral remote sensing imagery. IEEE Transactions on Geoscience and Remote Sensing, 2011, 50(3): 894–909

    Article  MathSciNet  Google Scholar 

  2. Pushmeet K, Lubor L, Philip H. Robust higher order potentials for enforcing label consistency. International Journal of Computer Vision, 2009, 82(3): 302–324

    Article  Google Scholar 

  3. Lubor L. Global structured models towards scene understanding. Dissertation for the Doctoral Degree. Oxford: Oxford Brooks Univerty, 2011

    Google Scholar 

  4. Yang Y, Wu F, Nie F, Shen H, Zhuang Y, Alexander G. Web and personal image annotation by mining label correlation with relaxed visual graph embedding. IEEE Transactions on Image Processing, 2012, 21(3): 1339–1351

    Article  MathSciNet  Google Scholar 

  5. Feng J, Jiao L, Zhang X, Sun T. Hyperspectral band selection based on trivariate mutual inforamtion and clonal selection. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(7): 4092–4105

    Article  Google Scholar 

  6. Qian D, He Y. Similarity-based unsupervised band selection for hyperspectral image analysis. IEEE Geoscience and Remote Sensing Letters, 2008, 5(4): 564–568

    Article  Google Scholar 

  7. Gustavo C, Joris M, Bernhard S. Remote sensing feature selection by kernel dependence measures. IEEE Geoscience and Remote Sensing Letters, 2010, 7(3): 587–591

    Article  Google Scholar 

  8. He Y, Qian D, Su H, Sheng Y. An efficient method for supervised hyperspectral band selection. IEEE Geoscience and Remote Sensing Letters, 2011, 8(1): 138–142

    Article  Google Scholar 

  9. Shen L, Zhu Z, Jia S, Zhu J, Sun Y. Discriminative gabor feature selection for hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters, 2013, 10(1): 29–33

    Article  Google Scholar 

  10. Qian Y, Ye M, Zhou J. Hyperspectral image classification based on structured sparse logistic regression and three-dimensional wavelet texure features. IEEE Transactions on Geoscience and Remote Sensing, 2012, 51(4): 2276–2291

    Article  Google Scholar 

  11. Claude C, Kacem C, Steven L. BandClust: an unsupervised band reduction method for hyperspectral remote sensing. IEEE Geoscience and Remote Sening Letters, 2011, 8(3): 565–569

    Article  Google Scholar 

  12. Chris B. Pattern Recognition and Machine Learning. Springer, 2006, 325–345

    Google Scholar 

  13. Cai X, Wen G, Wei J, Yu Z. Relative manifold based semi-supervised dimensionality. Frontiers of Computer Science, 2014, 8(6): 923–932

    Article  MathSciNet  Google Scholar 

  14. Li W, Guo Q, Charles E. A positive and unlabeled learning algorithm for one-class classification of remote-sensing data. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(2): 717–725

    Article  Google Scholar 

  15. Priscilla R, Swamynathan S. A semi-supervised hierarchical approach: two dimensional clustering of microarray gene expression data. Frontiers of Computer Science, 2013, 7(2): 204–213

    Article  MathSciNet  Google Scholar 

  16. Yang L, Yang S, Jin P, Zhang R. Semis-upervised hyperspectral image classification using spatio-spectral laplacian support vector machine. IEEE Geoscience and Remote Sening Letters, 2014, 11(3): 651–655

    Article  MathSciNet  Google Scholar 

  17. Wei D, Melba M. Active learning via multi-view and local proximity co-regulatization for hyperspectral image classification. IEEE Journal of Selected Topics in Signal Processing, 2011, 5(3): 618–628

    Article  Google Scholar 

  18. Swarnajyoti P, Lorenzo B. A fast cluster-assumption based activelearning technique for classification of remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(5): 1617–1626

    Article  Google Scholar 

  19. Begum D, Claudio P, Lorenzo B. Batch-mode active-learning methods for the interactive classification of remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(3): 1014–1031

    Article  Google Scholar 

  20. Gregg V, Robert O, Thomas G, Harry T, Earl G, Wallace M. The airboren visible/infrared imaging spectrometer. Remote Sensing of Enviroment, 1993, 44(3): 127–143

    Google Scholar 

  21. Joseph L, Nicewander W. Thirteen ways to look at the correlation coefficient. The American Statistician, 1988, 42(1): 59–66

    Google Scholar 

  22. Warner T, Steinmaus K, Foote B. An evaluation of spatial autocorrelation feature selection. International Jounral of Remote Sensing, 1999, 20(8): 1601–1606

    Article  Google Scholar 

  23. Masashi S. Dimensionality reduction of multimodal labeled data by local fisher discriminant analysis. Journal of Machine Learning Research, 2007, 8(3): 1027–1061

    MATH  Google Scholar 

  24. Landgrebe D. Signal Theory Methods in Multispectral Remote Sensing. Hoboken: Wiley, 2003

    Book  Google Scholar 

  25. Yu X, Yang J, Xie Z. Training SVMs on a bound vectors set based on fisher projection. Frontiers of Computer Science, 2014, 8(5): 793–806

    Article  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute of Communications Engineering, PLA University of Science and Technology, Nanjing, 210007, China

    Lu Yu & Lei Zhu

  2. College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016, China

    Lu Yu & Songcan Chen

  3. College of Command Information System, PLA University of Science and Technology, Nanjing, 210007, China

    Jun Xie

Authors
  1. Lu Yu
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Jun Xie
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Songcan Chen
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Lei Zhu
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Songcan Chen.

Additional information

Lu Yu received her BS, MS and PhD respectively from PLA Institute of Communications Engineering, China, PLA University of Science and Technology, China, SouthEast University, China in 1996, 2000 and 2007. Since 2000, she has been with Institute of Communications Engineering, PLA University of Science and Technology. Now she is a postdoctor of Nanjing University of Aeronautics and Astronautics, China. Her current research interests include image understanding, image processing and pattern recognition.

Jun Xie received his BS and MS from PLA Institute of Communications Engineering, China in 1995 and 1999 respectively. He received his PhD from Nanjing University, China in 2005. Since 1999, he has been with the College of Command Information System, PLA University of Science and Technology, China. His current research interests include data analysis and visualization, intelligent network management.

Songcan Chen received his BS, MS and PhD respectively from Hangzhou University (now merged into Zhejiang University), China, Shanghai JiaoTong University, China and Nanjing University of Aeronautics and Astronautics (NUAA), China in 1983, 1985 and 1997. He joined in NUAA in 1986, and since 1998, he has been a full-time professor with the College of Computer Science. He has authored/coauthored over 170 scientific peer-reviewed papers and ever obtained Biennial Honorable Mentions of 2006, 2007 and 2010 Best Paper Awards of Pattern Recognition Journal respectively. His current research interests include pattern recognition, machine learning, and neuralcomputing.

Lei Zhu received his BS and MS from PLA Institute of Communications Engineering, China in 1996 and 1999. He received his PhD from PLA University of Science and Technology, China in 2003. Since 1999, he has been with Institute of Communications Engineering, PLA University of Science and Technology. His current research interests include intelligent information process, intelligent network management.

Electronic supplementary material

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yu, L., Xie, J., Chen, S. et al. Generating labeled samples for hyperspectral image classification using correlation of spectral bands. Front. Comput. Sci. 10, 292–301 (2016). https://doi.org/10.1007/s11704-015-4103-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11704-015-4103-4

Keywords