Skip to main content
SpringerLink
Log in

Improved Fukunaga–Koontz Transform with Compositional Kernel Combination for Hyperspectral Target Detection

  • Research Article
  • Published:
Journal of the Indian Society of Remote Sensing Aims and scope Submit manuscript

Abstract

This article presents a novel supervised target detection approach on hyperspectral images based on Fukunaga–Koontz Transform (FKT) with compositional kernel combination. The Fukunaga–Koontz Transform is one of the most effective techniques for solving problems that involve two-pattern characteristics. To capture nonlinear properties of data, researchers have extended FKT to kernel FKT (KFKT) by means of kernel machines. However, the performance of KFKT depends on choosing convenient kernel functions and/or selection of the proper parameter(s). In this work, instead of selecting a single kernel for nonlinear version of FKT, we have applied a compositional kernel combination approach to capture the underlying local distributions of hyperspectral remote sensing data. Optimal parameter selection for each kernel function is achieved applying an evolutionary technique called differential evolution algorithm. The proposed new nonlinear target detection algorithm is tested for hyperspectral images. The experimental results verify that the proposed target detection algorithm has effective and promising performance compared to the conventional version for supervised target detection applications.

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

Similar content being viewed by others

References

  • Aizerman, M., Braverman, E., & Rozonoer, L. (1964). Theoretical foundations of the potential function method in pattern recognition learning. Automation and Remote Control, 25, 821–837.

    Google Scholar 

  • AVIRIS NW Indiana’s Indian Pines 1992 Data Set. (Original files) and (groundtruth). https://engineering.purdue.edu/~biehl/MultiSpec/hyperspectral.htmlaccessed: (25.03.2013).

  • Bach, F. R., Lanckriet, G. R. G., & Jordan, M. I. (2004). Multiple kernel learning, conic duality, and the SMO algorithm. In NIPS.

  • Bal, A., & Alam, M. S. (2005). Quadratic correlation filter-based target tracking in FLIR image sequences. Proceedings of SPIE Applications of Digital Image Processing XXVIII, 5909, 590906.

    Article  Google Scholar 

  • Binol, H., & Bal, A. (2016). Supervised target detection in hyperspectral images using one-class Fukunaga–Koontz transform. In Signal Processing, Sensor/Information Fusion, and Target Recognition XXV (vol. 9842). International Society for Optics and Photonics.

  • Binol, H., Bal, A., Cukur, H. (2015a). Differential evolution algorithm-based kernel parameter selection for Fukunaga–Koontz transform subspaces construction. In High-Performance Computing in Remote Sensing V (vol. 9646). International Society for Optics and Photonics.

  • Binol, H., Bilgin, G., Dinc, S., & Bal, A. (2015b). Kernel Fukunaga–Koontz transform subspaces for classification of hyperspectral images with small sample sizes. IEEE Geoscience and Remote Sensing Letters, 12(6), 1287–1291.

    Article  Google Scholar 

  • Binol, H., Ochilov, S., Alam, M.S., Bal, A. (2017). Target oriented dimensionality reduction of hyperspectral data by Kernel Fukunaga–Koontz transform. Optics and Lasers in Engineering, 89, 123–130.

    Article  Google Scholar 

  • Chang, H., Koschan, A., Abidi, B., & Abidi, M. (2010). Fusing continuous spectral images for face recognition under indoor and outdoor illuminants. Machine Vision and Applications, 21(2), 201–215.

    Article  Google Scholar 

  • Dinc, S., & Bal, A. (2013). Hyperspectral image classification using kernel Fukunaga–Koontz transform. Mathematical Problems in Engineering, 2013, 1–7.

    Article  Google Scholar 

  • Faulconbridge, R. I., & Pickering, M. R. (2006). Unsupervised band removal leading to improved classification accuracy of hyperspectral images. In Proceedings of the 29th Australasian computer science conference, June 2006, Australia.

  • Fukunaga, K., & Koontz, W. L. G. (1970). Applications of the Karhunen–Loève expansion to feature selection and ordering. IEEE Transaction on Computers, 19(5), 311–318.

    Article  Google Scholar 

  • Huo, X. et al. (2003a). Optimal reduced-rank quadratic classifiers using the Fukunaga–Koontz transform with applications to automated target recognition. In AeroSense 2003. International Society for Optics and Photonics.

  • Huo, X. et al. (2003b). Optimal reduced-rank quadratic classifiers using the Fukunaga–Koontz transform with applications to automatic target recognition. In Proceedings of SPIE (Vol. 5094).

  • Kim, K., Franz, M. O., & Schölkopf, B. (2005). Iterative kernel principal component analysis for image modeling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(9), 1351–1366.

    Article  Google Scholar 

  • Lanckriet, G. R. G., Cristianini, N., Bartlett, P., El Ghaoui, L., & Jordan, M. I. (2004). Learning the kernel matrix with semidefinite programming. Journal of Machine Learning Research, 5, 27–72.

    Google Scholar 

  • Lee, W.-J., Verzakov, S., & Duin, R. P. W. (2007). Kernel combination versus classifier combination. In Proceedings of the 7th international conference on multiple classifier systems (pp. 22–31). Berlin, Heidelberg: Springer.

  • Li, Y.-H. & Savvides, M. (2007). Kernel Fukunaga–Koontz transform subspaces for enhanced face recognition. In IEEE conference on computer vision and pattern recognition (CVPR 2007), June 2007 (pp 1–8).

  • Liang, Z., & Li, Y. (2010). Multiple kernels for generalised discriminant analysis. IET Computer Vision, 4(2), 117–128.

    Article  Google Scholar 

  • Liu, R., Liu, E., Yang, J., Zhang, T., & Wang, F. (2007). Infrared small target detection with kernel Fukunaga–Koontz transform. Measurement Science & Technology, 18(9), 3025–3035.

    Article  Google Scholar 

  • Ljungqvist, M. G., Nielsen, O. H. A., Frosch, S., Nielsen, M. E., Clemmensen, L. H., & Ersboll, B. K. (2014). Hyperspectral imaging based on diffused laser light for prediction of astaxanthin coating concentration. Machine Vision and Applications, 25(2), 327–343.

    Article  Google Scholar 

  • Mahalanobis, A., Muise, R. R., Stanfill, S. R., & Nevel, A. V. (2004). Design and application of quadratic correlation filters for target detection. IEEE Transactions on Aerospace and Electronic Systems, 40(3), 837–850.

    Article  Google Scholar 

  • Manolakis, D., & Shaw, G. (2002). Detection algorithms for hyperspectral imaging applications. IEEE Signal Processing Magazine, 19(1), 29–43.

    Article  Google Scholar 

  • Ong, C. S., Smola, A. J., & Williamson, R. C. (2005). Learning the kernel with hyperkernels. Journal of Machine Learning Research, 6, 1043–1071.

    Google Scholar 

  • Peng, J., Douglas, R. H., & Dai, H. K. (2004). Adaptive quasiconformal kernel nearest neighbor classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(5), 656–661.

    Article  Google Scholar 

  • Qian, Yuntao, Yao, Futian, & Jia, Sen. (2009). Band selection for hyperspectral imagery using affinity propagation. IET Computer Vision, 3(4), 213–222.

    Article  Google Scholar 

  • Rajadell, O., & Garc´ıa-Sevilla, P. (2009). Textural features for hyperspectral pixel classification. In Proceedings of the 4th Iberian conference on pattern recognition and image analysis, June 2009, Portugal.

  • Shawe-Taylor, J., & Cristianini, N. (2004). Kernel methods for pattern analysis. Cambridge: Cambridge University Press.

    Book  Google Scholar 

  • Sims, S. R. F., & Mahalanobis, A. (2004). Performance evaluation of quadratic correlation filters for target detection and discrimination in infrared imagery. Optical Engineering, 43, 1705–1711.

    Article  Google Scholar 

  • Snyder, D., Kerekes, J., Fairweather, I., Crabtree, R., Shive, J., & Hager, S. (2008) Development of a web-based application to evaluate target finding algorithms. In Proceedings of IEEE international geoscience and remote sensing symposium, Jul. 2008 (Vol. 2, pp. 915–918).

  • Storn, R., & Price, K. (1997). Differential evolution—a simple and efficient heuristic for global optimization over continuous spaces. Journal of Global Optimization, 11(4), 341–359.

    Article  Google Scholar 

  • Xu, X., Tsang, I. W., & Xu, D. (2013). Soft margin multiple kernel learning. IEEE Transactions on Neural Networks and Learning Systems, 24(5), 749–761.

    Article  Google Scholar 

  • Yang, M.-H., Kriegman, D. J., & Ahuja, N. (2002). Detecting faces in images: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(1), 34–58.

    Article  Google Scholar 

  • Zhang, D.-Q., Zhou, Z.-H., & Chen, S. C. (2006). Adaptive kernel principal component analysis with unsupervised learning of kernels. In Proceedings of the 6th IEEE international conference on data mining (ICDM) (pp. 1178–1182).

Download references

Author information

Authors and Affiliations

  1. Department of Electrical and Computer Engineering, Florida International University, Miami, FL, 33174, USA

    Hamidullah Binol

Authors
  1. Hamidullah Binol
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hamidullah Binol.

Ethics declarations

Conflict of interest

The author declares that he has no conflict of interest.

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Binol, H. Improved Fukunaga–Koontz Transform with Compositional Kernel Combination for Hyperspectral Target Detection. J Indian Soc Remote Sens 46, 1605–1615 (2018). https://doi.org/10.1007/s12524-018-0814-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12524-018-0814-y

Keywords

Search

Navigation