Skip to main content
SpringerLink
Log in

Clustering-Based Extraction of Near Border Data Samples for Remote Sensing Image Classification

  • Published:
Cognitive Computation Aims and scope Submit manuscript

Abstract

The definition of valuable training samples and automatic classification of land cover with remote sensing data are both classical problems, which are known to be difficult and have attracted major research efforts. In this paper, a method of modified K-means-based support vector machine (SVM) classification is proposed to use a hybrid sample selection that leverages the informativeness and representativeness of training samples to classify real multi/hyperspectral images. The hybrid sample selection (close-to-cluster-border sampling and near-cluster-center sampling) is constructed on the reduced convex hulls (RCHs) of clustering structure and can reduce the risk of overtraining caused by active sample selection of active learning methods. Numerical results obtained on the classification of three challenging remote sensing images (Landsat-7 ETM+, AVIRIS Indian pines, and KSC) by comparing the proposed technique with random sampling (RS) and margin sampling (MS) demonstrate the good efficiency and high accuracy of our approach.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  1. Tarabalka Y, Benediktsson JA, Chanussot J. Spectral-spatial classification of hyperspectral imagery based on partitional clustering techniques. IEEE Trans Geosci Remote Sens. 2009;47(8):2973–87.

    Article  Google Scholar 

  2. Camps-Valls G, Bruzzone L. Introduction to the issue on advances in remote sensing image processing. IEEE J Sign Process. 2011;5(3):365–9.

    Google Scholar 

  3. Camps-Valls G, Marsheva B, Zhou D. Semi-supervised graph-based hyperspectral image classification. IEEE Trans Geosci Remote Sens. 2007;45(10):3044–54.

    Article  Google Scholar 

  4. Bruzzone L, Chi M, Marconcini M. A novel transductive SVM for semisupervised classification of remote-sensing images. IEEE Trans Geosci Remote Sens. 2006;44(11):3363–73.

    Article  Google Scholar 

  5. Li Y, Chung SM. Parallel bisecting K-means with prediction clustering algorithm. J Supercomput. 2007;39(1):19–37.

    Article  Google Scholar 

  6. Tuia D, Kanevski M, Mart JM, Camps-Valls G. Cluster-based active learning for compact image classification. In: Proceedings of. IGARSS, US; 2010, pp 2824–27.

  7. Mitra P, Shankar BU, Pal SK. Segmentation of multispectral remote sensing images using active support vector machines. Pattern Recognit Lett. 2004;25(9):1067–74.

    Article  Google Scholar 

  8. Volpi M, Tuia D, Kanevski M. Advanced active sampling for remote sensing image classification. In Proceedings of IEEE IGARSS, US; 2010, pp 1–4.

  9. Patra S, Bruzzone L. A fast cluster-assumption based active-learning technique for classification of remote sensing images. IEEE Trans Geosci Remote Sens. 2011;49(5):1617–26.

    Article  Google Scholar 

  10. Rajan S, Ghosh J, Crawford MM. An active learning approach to hyperspectral data classification. IEEE Trans Geosci Remote Sens. 2008;46(4):1231–42.

    Article  Google Scholar 

  11. Cohn D, Ghahramani Z, Jordan MI. Active learning with statistical models. J Artif Intell Res. 1996;4:129–45.

    Google Scholar 

  12. Kruse FA, Lefkoff AB, Boardman JW, Heidebrecht KB, Shapiro AT, Barloon PJ, Goetz AFH. The spectral image processing system (SIPS)—interactive visualization and analysis of imaging spectrometer data. Remote Sens Environ. 1993;44:145–63.

    Article  Google Scholar 

  13. Schohn G, Cohn D. Less is more: active learning with support vector machines. In Proceedings of ICML; 2000, pp 839–46.

  14. Tong S, Koller D. Support vector machine active learning with applications to text classification. J Mach Learn Res. 2001;2:45–66.

    Google Scholar 

  15. Demir B, Persello C, Bruzzone L. Batch mode active learning methods for the interactive classification of remote sensing images. IEEE Trans Geosci Remote Sens. 2010;49(3):1014–31.

    Article  Google Scholar 

  16. Tuia D, Ratle F, Kanevski MF, Emery WJ. Active learning methods for remote sensing image classification. IEEE Trans Geosci Remote Sens. 2009;47(7):2218–32.

    Article  Google Scholar 

  17. Vovk V, Gammerman A, Saunders C. Machine learning applications of algorithmic randomness. In Proceedings of ICML; 1999, pp 444–53.

  18. Proedrou K, Nouretdinov I, Vovk V, Gammerman A. Transductive conference machines for pattern recognition. In Proceedings of ECML; 2002, pp. 381–90.

  19. Ho SS, Wechsler H. Transductive confidence machine for active learning. In Proceedings of ICML; 2003, pp 1435–40.

  20. McCallum AK, Nigam K. Employing EM in pool-based active learning for text classification. In Proceedings of ICML, CA; 1998, pp 350–58.

  21. Demir B, Erturk S. Clustering-based extraction of border training patterns for accurate SVM classification of hyperspectral images. IEEE Geosci Remote Sens Lett. 2009;6(4):840–4.

    Article  Google Scholar 

  22. Huang SJ, Jin R, Zhou ZH. Active learning by querying informative and representative examples. In: Proceedings NIPS; 2010, pp 892–900.

  23. Liu ZB, Liu JG, Pan C, Wang GY. A novel geometric approach to binary classification based on scaled convex hulls. IEEE Trans Neural Netw. 2009;20(7):1215–20.

    Article  PubMed  Google Scholar 

  24. Scholkopf B, Smola AJ, Muller KR. Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput. 1998;10(5):1299–319.

    Article  Google Scholar 

  25. He XF, Niyogi P. Locality preserving projections. In Proceedings of NIPS, Canada; 2003.

  26. Tuia D, Kanevski M, Mart JM, Camps-Valls G. Cluster-based active learning for compact image classification. In: Proceedings of IGARSS, US; 2010, pp 2824–27.

  27. Rajan S, Ghosh J, Crawford MM. Exploiting class hierarchies for knowledge transfer in hyperspectral data. IEEE Trans Geosci Remote Sens. 2006;44(11):3408–17.

    Article  Google Scholar 

  28. Chang CC, Lin CJ. LIBSVM: a library for support vector machines, 2001.

Download references

Acknowledgments

The authors would like to thank the anonymous reviewers for their constructive criticism and valuable suggestions on the original version of this paper, which helped improve this paper, and Prof. Landgrebe for the AVIRIS data and Prof. M. Crawford for the KSC data. This work was supported in part by National Natural Science Foundation of China (Nos. 60902060 and 60975031), the Program of Wuhan Subject Chief Scientist (201150530152), and the Project (2009CDA034) from Hubei Provincial Natural Science Foundation, China, and the Open Foundation (2010D11) of State Key Laboratory of Bioelectronics, Southeast University.

Author information

Authors and Affiliations

  1. Institute for Pattern Recognition and Artificial Intelligence, Huazhong University of Science and Technology, Wuhan, 430074, China

    Xiaoyong Bian, Tianxu Zhang & LuXin Yan

  2. School of Computer Science, Wuhan University of Science and Technology, Wuhan, 430065, China

    Xiaoyong Bian, Xiaolong Zhang & Bo Li

Authors
  1. Xiaoyong Bian
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tianxu Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiaolong Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. LuXin Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Bo Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xiaoyong Bian.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Bian, X., Zhang, T., Zhang, X. et al. Clustering-Based Extraction of Near Border Data Samples for Remote Sensing Image Classification. Cogn Comput 5, 19–31 (2013). https://doi.org/10.1007/s12559-012-9147-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12559-012-9147-2

Keywords

Search

Navigation