volume | PIER Journals

Abstract

This paper proposes a hybrid classifier for polarimetric SAR images. The feature sets consist of span image, the H/A/α decomposition, and the gray-level co-occurrence matrix (GLCM) based texture features. Then, the features are reduced by principle component analysis (PCA). A 3-layer neural network (NN) is constructed, trained by resilient back-propagation (RPROP) method to fasten the training and early stop (ES) method to prevent the overfitting. The results of San Francisco and Flevoland site compared to Wishart Maximum Likelihood and wavelet-based method demonstrate the validness of our method in terms of confusion matrix and overall accuracy. In addition, NNs with and without PCA are compared. Results show the NN with PCA is more accurate and faster.

1. Lee, J. S., M. R. Grunes, and R. Kwok, "Classification of multi-look polarimetric SAR imagery based on complex Wishart distribution," Int. J. Remote Sensing, Vol. 15, No. 11, 2299-2311, 1994.
doi:10.1080/01431169408954244 Google Scholar

2. Yang, S. Y., M. Wang, and L. C. Jiao, "Radar target recognition using contourlet packet transform and neural network approach," Signal Processing, Vol. 89, No. 4, 394-409, 2009.
doi:10.1016/j.sigpro.2008.09.015 Google Scholar

3. Chen, C. H. and P.-G. P. Ho, "Statistical pattern recognition in remote sensing," Pattern Recognition, Vol. 41, No. 9, 2731-2741, 2008.
doi:10.1016/j.patcog.2008.04.013 Google Scholar

4. Kasturirangan, K., "Space technology for humanity: A profile for the coming 50 years," Space Policy, Vol. 23, No. 3, 159-166, 2007.
doi:10.1016/j.spacepol.2007.06.015 Google Scholar

5. Makal, S., A. Kizilay, and L. Durak, "On the target classification through wavelet-compressed scattered ultrawide-band electric field data and ROC analysis," Progress In Electromagnetics Research, Vol. 82, 419-431, 2008.
doi:10.2528/PIER08040903 Google Scholar

6. Rostami, A. and A. Yazdanpanah-Goharriz, "A new method for classification and identification of complex fiber bragg grating using the genetic algorithm," Progress In Electromagnetics Research, Vol. 75, 329-356, 2007.
doi:10.2528/PIER07061802 Google Scholar

7. Khan, K. U. and J. Yang, "Polarimetric synthetic aperture radar image classification by a hybrid method," Tsinghua Science and Technology, Vol. 12, No. 1, 97-104, 2007.
doi:10.1016/S1007-0214(07)70015-9 Google Scholar

8. Castaldi, G., V. Galdi, and G. Gerini, "Evaluation of a neural-network-based adaptive beamforming scheme with magnitude-only constraints," Progress In Electromagnetics Research B, Vol. 11, 1-14, 2009.
doi:10.2528/PIERB08092303 Google Scholar

9. Li, X. and J. Gao, "Pad modeling by using artificial neural network," Progress In Electromagnetics Research, Vol. 74, 167-180, 2007.
doi:10.2528/PIER07041201 Google Scholar

10. Cloude, S. R. and E. Pottier, "A review of target decomposition theorems in radar polarimetry," IEEE Trans. Geosci. Remote Sensing, Vol. 34, No. 2, 498-518, 1996.
doi:10.1109/36.485127 Google Scholar

11. Cooper, G. R. J. and D. R. Cowan, "The use of textural analysis to locate features in geophysical data," Computers & Geosciences, Vol. 31, No. 7, 882-890, 2005.
doi:10.1016/j.cageo.2005.02.001 Google Scholar

12. Mandal, S., P. V. Sivaprasad, S. Venugopal, and K. P. N. Murthy, "Artificial neural network modeling to evaluate and predict the deformation behavior of stainless steel type AISI 304L during hot torsion," Applied Soft Computing, Vol. 9, No. 1, 237-244, 2009.
doi:10.1016/j.asoc.2008.03.016 Google Scholar

13. Luukka, P., "Classification based on fuzzy robust PCA algorithms and similarity classifier," Expert Systems with Applications, Vol. 36, No. 4, 7463-7468, 2009.
doi:10.1016/j.eswa.2008.09.015 Google Scholar

14. Durrington, P. N., V. Charlton-Menys, C. J. Packard, et al. "Familial hypobetalipoproteinemia due to a novel early stop mutation," Journal of Clinical Lipidology, Vol. 2, No. 5, 384-390, 2008.
doi:10.1016/j.jacl.2008.08.446 Google Scholar

15. Shyu, J.-J., C.-H. Chan, M.-W. Hsiung, P.-N. Yang, H.-W. Chen, and W.-C. Kuo, "Diagnosis of articular cartilage damage by polarization sensitive optical coherence tomography and the extracted optical properties," Progress In Electromagnetics Research, Vol. 91, 365-376, 2009.
doi:10.2528/PIER09022602 Google Scholar

16. Cloude, S. R. and E. Pottier, "An entropy based classification scheme for land applications of polarimetric SAR," IEEE Trans. Geosci. Remote Sensing, Vol. 35, No. 1, 549-557, 1997.
doi:10.1109/36.551935 Google Scholar

17. Duan, Y., S.-J. Lai, and T. Huang, "Coupling projection domain decomposition method and meshless collocation method using radial basis functions in electromagnetics," Progress In Electromagnetics Research Letters, Vol. 5, 1-12, 2008.
doi:10.2528/PIERL08092003 Google Scholar

18. Pottier, E. and S. R. Cloude, "Application of the H/A/α polarimetric decomposition theorems for land classification ," Proc. SPIE Conference on Wideband Interferometric Sensing and Imaging Polarimetry, 132-143, San Diego, CA, USA, 1997. Google Scholar

19. Tien, C. L., Y. R. Lyu, and S. S. Jyu, "Surface flatness of optical thin films evaluated by gray level co-occurrence matrix and entropy," Applied Surface Science, Vol. 254, 4762-4767, 2008.
doi:10.1016/j.apsusc.2008.01.088 Google Scholar

20. Bermani, E., S. Caorsi, and M. Raffetto, "An inverse scattering approach based on a neural network technique for the detection of dielectric cylinders buried in a lossy half-space," Progress In Electromagnetics Research, Vol. 26, 67-87, 2000.
doi:10.2528/PIER99052001 Google Scholar

21. Luukka, P., "Classification based on fuzzy robust PCA algorithms and similarity classifier," Expert Systems with Applications, Vol. 36, No. 4, 7463-7468, 2009.
doi:10.1016/j.eswa.2008.09.015 Google Scholar

22. Zainud-Deen, S. H., H. A. El-Azem Malhat, K. H. Awadalla, and E. S. El-Hadad, "Direction of arrival and state of polarization estimation using radial basis function neural network (RBFNN)," Progress In Electromagnetics Research B, Vol. 2, 137-150, 2008.
doi:10.2528/PIERB07111801 Google Scholar

23. Zhang, Y. D. and L. Wu, "Weights optimization of neural network via improved BCO approach," Progress In Electromagnetics Research, Vol. 83, 185-198, 2008.
doi:10.2528/PIER08051403 Google Scholar

24. Riedmiller, M. and H. Braun, "A direct adaptive method for faster backpropagation learning: The RPROP algorithm," Proceedings of the IEEE International Conference on Neural Networks, 586-591, San Francisco, 1993. Google Scholar

25. Lee, Y. H. and S. Y. Huang, "Electromagnetic susceptibility of an electromagnetic band-gap filter structure," Progress In Electromagnetics Research B, Vol. 15, 31-56, 2009.
doi:10.2528/PIERB09042211 Google Scholar

26. Gupta, K. K. and R. Gupta, "Despeckle and geographical feature extraction in SAR images by wavelet transform," ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 62, No. 6, 473-484, 2007.
doi:10.1016/j.isprsjprs.2007.06.001 Google Scholar

27. Fukuda, S. and H. Hirosawa, "A wavelet-based texture feature set applied to classification of multifrequency polarimetric SAR images," IEEE Trans. on Geoscience and Remote Sensing, Vol. 37, No. 5, 2282-2286, 1999.
doi:10.1109/36.789624 Google Scholar

Prof. Yudong Zhang

Dr. Lenan Wu

Dr. Geng Wei