Robust Semi-supervised Kernel-FCM Algorithm Incorporating Local Spatial Information for Remote Sensing Image Classification

  • Chengjie Zhu
  • Shizhi Yang
  • Qiang Zhao
  • Shengcheng Cui
  • Nu Wen
Research Article
First Online:
Received:
Accepted:

Abstract

Fuzzy c-means (FCM) algorithm is a popular method in image segmentation and image classification. However, the traditional FCM algorithm cannot achieve satisfactory classification results because remote sensing image data are not subjected to Gaussian distribution, contain some types of noise, are nonlinear, and lack labeled data. This paper presents a robust semi-supervised kernel-FCM algorithm incorporating local spatial information (RSSKFCM_S) to solve the aforementioned problems. In the proposed algorithm, insensitivity to noise is enhanced by introducing contextual spatial information. The non-Euclidean structure and the problem in nonlinearity are resolved through kernel methods. Semi-supervised learning technique is utilized to supervise the iterative process to reduce step number and improve classification accuracy. Finally, the performance of the proposed RSSKFCM_S algorithm is tested and compared with several similar approaches. Experimental results for the multispectral remote sensing image show that the RSSKFCM_S algorithm is more effective and efficient.

Keywords

Kernel-FCM Remote sensing image Image classification Semi-supervised Local spatial information 
This is a preview of subscription content, log in to check access.

Notes

Acknowledgments

The authors would like to thank the anonymous referees for their helpful comments and suggestions to improve the presentation of the paper. Special thanks should be given to Dr. Banglong Pan and his colleagues, for providing the remote sensing image data for validation of our algorithm. This research was supported by Anhui Provincial Natural Science Foundation under Grant 1308085QD70.

References

  1. Ahmed, M. N., Yamany, S. M., Mohamed, N., Farag, A. A., Moriarty, T. (2002). A modified fuzzy C-means algorithm for bias field estimation and segmentation of MRI data. IEEE Transactions on Medical Imaging, 21, 193–199.Google Scholar
  2. Ben Hamza, A., & Krim, H. (2001). Image denoising: a nonlinear robust statistical approach. IEEE Transactions on Signal Processing, 49, 3045–3053.CrossRefGoogle Scholar
  3. Bensaid, A. M., Bezdek, J. C., & Hall, L. O. (1992). Partially supervised fuzzy c-means algorithm for segmentation of MR images. Proceedings of SPIE, Science of Artificial Neural Networks, 1710, 522–528.Google Scholar
  4. Bezdek, J. C. (1981). Pattern recognition with fuzzy objective function algorithms. NewYork: Plenum Press.CrossRefGoogle Scholar
  5. Bouchachia, A., & Pedrycz, W. (2006). Enhancement of fuzzy clustering by mechanisms of partial supervision. Fuzzy Sets and Systems, 157, 1733–1759.CrossRefGoogle Scholar
  6. Cai, W., Chen, S., & Zhang, D. (2007). Fast and robust fuzzy C-means clustering algorithms incorporating local information for image segmentation. Pattern Recognition, 40, 825–838.CrossRefGoogle Scholar
  7. Chen, S., & Zhang, D. (2004). Robust image segmentation using FCM with spatial constraints based on new Kernel-induced distance measure. IEEE Transactions on Systems Man and Cybernetics Part B, 34, 1907–1916.CrossRefGoogle Scholar
  8. Liew, A. W. C., Leung, S. H., & Lau, W. H. (2000). Fuzzy image clustering incorporating spatial continuity. Institute of Electrical Engineers Vision, Image and Signal Processing, 147, 185–192.CrossRefGoogle Scholar
  9. Liu, X., He, B., & Li, X. (2008). Semi-supervised classification for hyperspectral remote sensing image based on PCA and kernel FCM algorithm. Proceedings of SPIE GIS and Built Environment, 7147, 1–10.Google Scholar
  10. Pal, N. R., & Bezdek, J. C. (1995). On cluster validity for the fuzzy c-means model. IEEE Transactions on Fuzzy Systems, 3, 370–379.CrossRefGoogle Scholar
  11. Pham, D. L. (2002). Fuzzy clustering with spatial constraints. In IEEE Proc. Int. Conf. Image Processing, NewYork, pp. II-65–II-68.Google Scholar
  12. Rafael, W. (1997). Unsupervised fuzzy classification of multispectral imagery using spatial-spectral features. 21st Annual Meeting of the Gesellschaft fur Klassikation, GfKl’97, Potsdam.Google Scholar
  13. Tamma, R., Rao, T. C. M., & Jaisankar, G. (2011). An efficient method for joint spatial and spectral classification of remote sensed images. International Journal of Computer Science and Telecommunications, 2, 262–265.Google Scholar
  14. Xiaorui, Lv. (2008). Model simulation and parameter estimation of alpha stable distribution. Master Dissertation, Huazhong University of Science & Technology, China.Google Scholar
  15. Yang, Y., Guo, S-X., Ren, R-Z., Yu, Y-L. (2011). Modified kernel-based fuzzy C-means algorithm with spatial information for image segmentation. Journal of Jilin University (Engineering and Technology Edition), 41, 283–287.Google Scholar

Copyright information

© Indian Society of Remote Sensing 2013

Authors and Affiliations

  • Chengjie Zhu
    • 1
    • 2
    • 3
  • Shizhi Yang
    • 1
  • Qiang Zhao
    • 1
  • Shengcheng Cui
    • 1
  • Nu Wen
    • 1
  1. 1.Center of Optical Remote Sensing, Anhui Institute of Optics and Fine MechanicsChinese Academy of SciencesHefeiChina
  2. 2.College of Electronic EngineeringAnhui University of Science and TechnologyHuainanChina
  3. 3.HuaibeiChina

Personalised recommendations