Skip to main content
SpringerLink
Log in

Multidimensional local spatial autocorrelation measure for integrating spatial and spectral information in hyperspectral image band selection

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Hyperspectral band selection aims at the determination of an optimal subset of spectral bands for dimensionality reduction without loss of discriminability. Many conventional band selection approaches depend on the concept of “statistical distance” measure between the probability distributions characterizing sample classes. However, the maximization of separability does not necessarily guarantee that a classification process results in the best classification accuracies. This paper presents a multidimensional local spatial autocorrelation (MLSA) measure that quantifies the spatial autocorrelation of the hyperspectral image data. Based on the proposed spatial measure, a collaborative band selection strategy is developed that combines both spectral separability measure and spatial homogeneity measure for hyperspectral band selection without losing the spectral details useful in classification processes. The selected band subset by the proposed method shows both larger separability between classes and stronger spatial similarity within class. Case studies in biomedical and remote sensing applications demonstrate that the MLSA-based band selection approach improves object classification accuracies in hyperspectral imaging compared with conventional approaches.

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

Similar content being viewed by others

References

  1. Anselin L (1995) Local indicators of spatial association—LISA. Geogr Anal 27:93–115

    Article  Google Scholar 

  2. Beigi M, Chang S, Ebadollahi S, Verma D (2009) Multi-scale temporal segmentation and outlier detection in sensor networks. IEEE International Conference on Multimedia and Expo, pp. 306–309

  3. Bruzzone L, Roli F, Serpico S (1995) An extension of the Jeffreys-Matusita distance to multiclass cases for feature selection. IEEE Trans Geosci Remote Sens 33:1318–1321

    Article  Google Scholar 

  4. Cliff A, Ord J (1981) Spatial Processes, Models and Applications. Pion, London

    MATH  Google Scholar 

  5. Du Z, Jeong M, Kong S (2007) Band selection of hyperspectral images for automatic detection of poultry skin tumors. IEEE Trans. Autom. Sci. Eng. 4(3):332–339

    Article  Google Scholar 

  6. Getis A, Ord J (1992) The analysis of spatial association by use of distance statistics. Geogr Anal 24:189–206

    Article  Google Scholar 

  7. Huang R, He M (2005) Band selection based on feature weighting for classification of hyperspectral data. IEEE Geosci Remote Sens Lett 2:156–159

    Article  Google Scholar 

  8. Jensen J (1996) Introductory digital image processing: a remote sensing perspective. Prentice-Hall, Englewood Cliffs

    Google Scholar 

  9. Jeong Y, Kim S, Jeong M (2008) Automatic identification of defect patterns in semiconductor wafer maps using spatial correlogram and dynamic time warping. IEEE Trans Semicond Manuf 21(4):625–637

    Article  MathSciNet  Google Scholar 

  10. Kong S, Chen Y, Kim I, Kim M (2004) Analysis of hyperspectral fluorescence images for poultry skin tumor inspection. Appl Opt 43(4):824–833

    Article  Google Scholar 

  11. Kononenko I (1994) Estimating attributes: analysis and extensions of RELIEF. In: Proceedings of seventh european conference on machine learning, pp 171–182

    Google Scholar 

  12. Kopisch M (1995) Spatial relations in technical domains. Appl Intell 5(4):351–366

    Article  Google Scholar 

  13. Landgrebe D (2002) Hyperspectral image data analysis as a high dimensional signal processing problem. IEEE Signal Process Mag 19(1):17–28

    Article  Google Scholar 

  14. Liu D, Setiono R (1998) Incremental feature selection. Appl Intell 9(3):217–230

    Article  Google Scholar 

  15. Milenova B, Campos M (2005) Mining high-dimensional data for information fusion: a database-centric approach. In: Proceedings of 8th international conference on information fusion, vol 1, pp 7–14

    Google Scholar 

  16. Park J, Jeong M (2010) Recursive support vector censored regression for monitoring product quality based on degradation profiles. in press. Applied Intelligence

  17. Schott J (2005) Matrix analysis for statistics, 2nd edn. Wiley, New Jersey

    MATH  Google Scholar 

  18. Serpico S, Moser G (2007) Extraction of spectral channels from hyperspectral images for classification purposes. IEEE Trans Geosci Remote Sens 45(2):484–495

    Article  Google Scholar 

  19. Simin C, Rongqun Z, Wenling C, Hui Y (2009) Band selection of hyperspectral image based on Bhattacharyya distance. WSEAS Trans Inf Sci Appl 6(7):1165–1175

    Google Scholar 

  20. Stein A, van der Meer F, Gorte B (1999) Spatial statistics for remote sensing. Kluwer Academic, Dordrecht

    Google Scholar 

  21. Swain P, King R (1973) Two effective feature selection criteria for multispectral remote sensing. In: Proceedings of the first international joint conference on pattern recognition, pp 536–540

    Google Scholar 

  22. Tu T, Chen C, Wu J, Chang C (1998) A fast two-stage classification method for high-dimensional remote sensing data. IEEE Trans Geosci Remote Sens 36:182–191

    Article  Google Scholar 

  23. Withagen P, Breejen F, Franken F, De Jong A, Winkel H (2001) Band selection from a hyperspectral data-cube for a real-time multispectral 3CCD camera. In: Proceedings of SPIE conference on algorithms for multispectral, hyperspectral, and ultraspectral imagery VII, vol 4381, pp 84–93

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electrical and Computer Engineering, The University of Tennessee, Knoxville, TN, 37996-2100, USA

    Zheng Du

  2. Department of Industrial and Systems Engineering, Rutgers University, Piscataway, NJ, 08854-8003, USA

    Young-Seon Jeong

  3. Department of Industrial and Systems Engineering, KAIST, Daejon, 305-701, Korea

    Myong K. Jeong

  4. Department of Electrical and Computer Engineering, Temple University, Philadelphia, PA, 19122, USA

    Seong G. Kong

  5. Department of Industrial and Systems Engineering & RUTCOR, Rutgers University, Piscataway, NJ, 08854-8003, USA

    Myong K. Jeong

Authors
  1. Zheng Du
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Young-Seon Jeong
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Myong K. Jeong
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Seong G. Kong
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Myong K. Jeong.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Du, Z., Jeong, YS., Jeong, M.K. et al. Multidimensional local spatial autocorrelation measure for integrating spatial and spectral information in hyperspectral image band selection. Appl Intell 36, 542–552 (2012). https://doi.org/10.1007/s10489-010-0274-8

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-010-0274-8

Keywords

Search

Navigation