Two Stage SVM Classification for Hyperspectral Data

Michal Cholewa, Przemyslaw Glomb

2016

Abstract

In this article, we present a method of enhancing the SVM classification of hyperspectral data with the use of three supporting classifiers. It is done by applying the fully trained classifiers on learning set to obtain the pattern of their behavior which then can be used for refinement of classifier construction. The second stage either is a straightforward translation of first stage, if the first stage classifiers agree on the result, or it consists of using retrained SVM classifier with only the data from learning data selected using first stage. The scheme shares some features with committee of experts fusion scheme, yet it clearly distinguishes lead classifier using the supporting ones only to refine its construction. We present the construction of two-stage scheme, then test it against the known Indian Pines HSI dataset and test it against straightforward use of SVM classifier, over which our method achieves noticeable improvement.

References

  1. Bhaskaran, S., Datt, B., Forster, T., T., N., and Brown, M. (2004). Integrating imaging spectroscopy (445-2543 nm) and geographic information systems for postdisaster management: A case of hailstorm damage in sydney. International Journal of Remote Sensing, 25(13):2625-2639.
  2. Bioucas-Dias, J. M., Plaza, A., Dobigeon, N., Parente, M., Du, Q., Gader, P., and Chanussot, J. (2012). Hyperspectral unmixing overview: Geometrical, statistical, and sparse regression-based approaches. Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of, 5(2):354-379.
  3. Chapelle, O., Haffner, P., and Vapnik, V. (1999). Support vector machines for histogram-based image classification. Neural Networks, IEEE Transactions on, 10(5):1055-1064.
  4. Chen, Y., Nasrabadi, N. M., and Tran, T. D. (2013). Hyperspectral image classification via kernel sparse representation. Geoscience and Remote Sensing, IEEE Transactions on, 51(1):217-231.
  5. Denoyer, L. and Gallinari, P. (2004). Bayesian network model for semi-structured document classification.Information Processing & Management, 40(5):807 - 827.
  6. Ellis, J. (2003). Hyperspectral imaging technologies key for oil seep/oil-impacted soil detection and environmental baselines. Environmental Science and Engineering. Retrieved on February, 23:2004.
  7. Fang, L., Li, S., Kang, X., and Benediktsson, J. A. (2015). Spectral-spatial classification of hyperspectral images with a superpixel-based discriminative sparse model. Geoscience and Remote Sensing, IEEE Transactions on, 53(8):4186-4201.
  8. Friedl, M. and Brodley, C. (1997). Decision tree classification of land cover from remotely sensed data. Remote Sensing of Environment, 61(3):399 - 409.
  9. Kuncheva, L. (2002). A theoretical study on six classifier fusion strategies. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 24(2):281-286.
  10. Kuncheva, L., Bezdek, J., and Duin, R. (2001). Decision templates for multiple classifier fusion: an experimental comparison. Pattern Recognition, 34:299-314.
  11. Manian, V. and Jimenez, L. O. (2007). Land cover and benthic habitat classification using texture features from hyperspectral and multispectral images. Journal of Electronic Imaging, 16(2):023011-023011-12.
  12. Melgani, F. and Bruzzone, L. (2004). Classification of hyperspectral remote sensing images with support vector machines. Geoscience and Remote Sensing, IEEE Transactions on, 42(8):1778-1790.
  13. Perrone, M. P. and Cooper, L. (1993). When networks disagree: Ensemble methods for hybrid neural networks. pages 126-142. Chapman and Hall.
  14. Pu, Y.-Y., Feng, Y.-Z., and Sun, D.-W. (2015). Recent progress of hyperspectral imaging on quality and safety inspection of fruits and vegetables: A review. Comprehensive Reviews in Food Science and Food Safety, 14(2):176-188.
  15. Rojas, M., D ópido, I., Plaza, A., and Gamba, P. (2010). Comparison of support vector machine-based processing chains for hyperspectral image classification. In SPIE Optical Engineering+ Applications, pages 78100B-78100B. International Society for Optics and Photonics.
  16. Ruta, D. and Gabrys, B. (2000). An overview of classifier fusion methods.
  17. Wolpert, D. (1992). Stacked generalization. Neural Networks, 5:241-259.
  18. Xu, L. and Li, J. (2014). Bayesian classification of hyperspectral imagery based on probabilistic sparse representation and markov random field. Geoscience and Remote Sensing Letters, IEEE, 11(4):823-827.
Download


Paper Citation


in Harvard Style

Cholewa M. and Glomb P. (2016). Two Stage SVM Classification for Hyperspectral Data . In Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-173-1, pages 387-391. DOI: 10.5220/0005828103870391


in Bibtex Style

@conference{icpram16,
author={Michal Cholewa and Przemyslaw Glomb},
title={Two Stage SVM Classification for Hyperspectral Data},
booktitle={Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2016},
pages={387-391},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005828103870391},
isbn={978-989-758-173-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Two Stage SVM Classification for Hyperspectral Data
SN - 978-989-758-173-1
AU - Cholewa M.
AU - Glomb P.
PY - 2016
SP - 387
EP - 391
DO - 10.5220/0005828103870391