Abstract

Texture feature is a predominant feature in land cover classification of remotely sensed images. In this study, texture features were extracted using the proposed multivariate descriptor, Multivariate Ternary Pattern (MTP). The soft classifiers such as Fuzzy k-Nearest Neighbor (Fuzzy k-NN), Support Vector Machine (SVM) and Extreme Learning Machine (ELM) were used along with the proposed multivariate descriptor for performing land cover classification. The experiments were conducted on IRS P6 LISS-IV data and the results were evaluated based on error matrix, classification accuracy and Kappa statistics. From the experiments, it was found that the proposed descriptor with SVM classifier gave 93.04% classification accuracy.

Keywords:

ELM , fuzzy k-NN , MTP , SVM , texture descriptor,

References

1. Demir, B. and S. Erturk, 2007. Hyperspectral image classification using relevance vector machines. IEEE Geosci. Remote S., 4(4): 586-590.
   CrossRef    
2. Hermes, L., D. Frieauff, J. Puzicha and J.M. Buhmann, 1999. Support vector machines for land usage classification in landsat TM imagery. Proceeding of the IEEE Geoscience and Remote Sensing Society Symposium, 1: 348-350.
   CrossRef    
3. Huang, G.B., 2003. Learning capability and storage capacity of two-hidden layer feedforward networks. IEEE T. Neural Networ., 14(2): 274-281.
   CrossRef    PMid:18238011    
4. Huang, G.B., Q.Y. Zhu and C.K. Siew, 2004. Extreme learning machine: A new learning scheme of feedforward neural networks. Proceeding of the International Joint Conference on Neural Networks (IJCNN, 2004). Budapest, Hungary, 2: 985-990.
   
5. Huang, G.B., Q.Y. Zhu and C.K. Siew, 2006. Extreme learning machine: Theory and applications. Neurocomputing, 70: 489-501.
   CrossRef    
6. Jae, Y.C., M.R. Yong and K.N. Plataniotis, 2012. Color local texture features for color face recognition. IEEE T. Image Process., 21(3): 1366-1380.
   CrossRef    PMid:21926019    
7. Jenicka, S. and A. Suruliandi, 2008. Comparative study of texture models using supervised segmentation. Proceeding of the 16th International Conference on Advanced Computing and Communications. MIT Campus, Anna University, Chennai.
   CrossRef    
8. Jenicka, S. and A. Suruliandi, 2011. Comparative study of classification algorithms with modified multivariate local binary pattern texture model on remotely sensed images. Proceeding of the International Conference on Recent Trends in Information Technology (ICRTIT, 2011). Chennai, Tamil Nadu, pp: 848-852.
   
9. Keller, J.M., M.R. Gray, J.A. Givens Jr., 1985. A fuzzy K-nearest neighbour algorithm. IEEE T. Syst. Man Cyb., SMC-15(4).
   
10. Liao, S. and A.C.S. Chung, 2007. Texture classification by using advanced local binary patterns and spatial distribution of dominant patterns. Proceeding of the IEEE International Conference Acoustics, Speech and Signal Processing (ICASSP, 2007).
    CrossRef    
11. Liao, S., M.W.K. Law and A.C.S. Chung, 2009. Dominant local binary patterns for texture classification. IEEE T. Image Process., 18(5): 1107-1118.
    CrossRef    PMid:19342342    
12. Lu, D. and Q. Weng, 2007. A survey of image classification methods and techniques for improving classification performance. Int. J. Remote Sens., 28(5): 823-870.
    CrossRef    
13. Lucieer, A., A. Stein and P. Fisher, 2005. Multivariate texture-based segmentation of remotely sensed imagery for extraction of objects and their uncertainty. Int. J. Remote Sens., 26(14): 2917-2936.
    CrossRef    
14. Ojala, T., M. Pietikainen and T. Maenpaa, 2001. A generalized local binary pattern operator for multiresolution gray scale and rotation invariant texture classification. In: Singh, S., N. Murshed and W. Kropatsch (Eds.), ICAPR, 2001. LNCS 2013, Springer-Verlag, Berlin, Heidelberg, pp: 399-408.
    CrossRef    
15. Qiu, Z.G., Ling and Qiong, 2008. High Efficient classification on SVM. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. 37. Part B2. Beijing.
    
16. Raju, U.S.N., A. Sridhar Kumar, B. Mahesh and E. Reddy, 2010. Texture classification with high order local pattern descriptor: Local derivative pattern. Global J. Comput. Sci. Technol., 10(8): 72-76.
    
17. Seung, H.L., Y.C. Jae, M.R. Yong and KN. Plataniotis, 2012. Local color vector binary patterns from multichannel face images for face recognition. IEEE T. Image Process., 21(4).
    
18. Suruliandi, A., 2009. A study on classification of remotely sensed multispectral mages-a textural approach. Ph.D. Thesis, Manonmaniam Sundaranar University, Tamil Nadu, India.
    
19. Suruliandi, A. and K. Ramar, 2008. Local texture patterns-a univariate texture model for classification of images. Proceeding of the 16th International Conference on Advanced Computing and Communications (ADCOM, 2008). Chennai, pp: 32-39.
    CrossRef    
20. Tanyildizi, E., 2012. A hybrid color texture image classification method based on 2D and semi 3D texture features and extreme learning machine. Prz. Elektrotechniczn., 11a: 358-362.
    
21. Turtinen, M., T. Mäenpää and M. Pietikäinen, 2003. Texture classification by combining local binary pattern features and a self-organizing map. Proceedings of the 13th Scandinavian Conference on Image Analysis (SCIA’ 03), pp: 1162-1169.
    CrossRef    
22. Wen, C. and J. Minhe, 2010. Comparative analysis of fuzzy approaches to remote sensing image classification. Proceeding of the 7th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD, 2010).
    
23. Xiaoyang, T. and T. Bill, 2007. Enhanced local texture feature sets for face recognition under difficult lighting conditions. Proceeding of the 3rd International Workshop Analysis and Modelling of Faces and Gestures (AMFG, 07), 4778: 168-182.
    
24. Younis, A.A., A.T. Soliman and N.M. John, 2007. Co-Segmentation of MR and MR spectroscopy imaging using hidden Markov models. Proceeding of the IEEE/NIH Life Science Systems and Applications Workshop (LISA, 2007). Bethesda, MD, pp: 188-191.
    CrossRef    

Competing interests

The authors have no competing interests.

Open Access Policy

This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Copyright

The authors have no competing interests.