Advanced Supervised Sub-Pixel Multi-Spectral Image Classifier

where n is the dimension of data;
While incorporating Support Vector Machine (SVM) algorithm, having constraint on their application in remote sensing due to its binary nature, requires multiclass classifications to be based upon a large number of binary analyses. In this algorithm density estimation has been done, which is based on the support vector machines (SVM) approach and it uses the Mean Field (MF) theory for developing an easy and efficient learning procedure for the SVM. It is well know that if data is non-separable training sets, than kernel functions can be used, which behaves like an inner product in high dimensions, to build a maximal margin hyperplane there, for separating out different classes. Different kernels used in SVM algorithm incorporated in this system are; Gaussian Kernel, Radial Basis, KMOD, Inverse Multiquadric, Linear Kernel, Polynomial Kernel, Sigmoid Kernel, Spectral Kernel. Also there is the provision kept in this system that mixed kernel can be generated will using any of the two kernel in combination.

As it is well known that in supervised classification reference data is required. This reference data can be generated from this system in two modes i.e. pure reference data as well as mixed reference data. Reference data in pure or in mixed form can be used to all the classification algorithms incorporated in this system for generating fraction images. There is also provision in this system for saving the membership values generated using different classifiers for sup-pixel classification.

Accuracy assessment is very critical component in classification for assessing the accuracy of fraction images generated using sub-pixel classifier. As this system is capable for generating hard as well as sub-pixel level outputs, so for both types of outputs, different accuracy assessment methods have been incorporated. For hard classification output error matrix as well as Khat coefficient have been used for assessing the accuracy of classified output. For sup-pixel classification, when reference as well as output is soft, Fuzzy Error Matrix (FERM) has been incorporated in this system for assessing the accuracy of soft classified output.

Generation of output:
The outputs from this system can be generated in hard as well as in soft classification (fraction images). For an example fraction images generated using possibilistic Fuzzy c-means algorithm had been shown in figure 2. In this total six land cover classes were taken and signature data for each land cover class were generated. Using these signature data fraction images for each land cover class were generated and output pixel value were represented between o to 1 membership value.

Conclusions and Future Scope:
The main objective of developing SMIC (Sub-Pixel Multi-Spectral Image Classifier) in JAVA programming language is to provide resources management professionals the confidence to learn and use the sub-pixel classification approach. At present, there is hardly any commercial digital image processing systems dedicated to advanced sub-pixel classifier are available and if available, they are than it is very costly. This system has been developed in a very graphical user-friendly environment, so that any resources management professionals can easily use this system and learn the supervised fuzzy sub-pixel classifier approach. As this system is developed in JAVA environment, so this system is platform independent. This software is a basic version presently and is being updated and refined to incorporate many other aspects of image processing.











Figure No. 2: Fraction of Images generated from SMIC System


Reference:
  1. Atkinson, P. M., and Tatnall, A. R. L., 1997, Neural networks in remote sensing. International Journal of Remote Sensing, 18, 699-709.
  2. Brodley, C. E., and Utgoff, P. E., 1995, Multivariate decision trees. Machine L earning, 19, 45-77.
  3. C. Huang, L. S. Davis, J. R. G. Townshend, 2002," An assessment of support vector machines for land cover classification" IJRS, vol. 23, no. 4, 725-749.
  4. DeFries, R. S., Hansen, M., Townshend, J. R. G., and Sohlberg, R., 1998, Global land cover classi. cations at 8km spatial resolution: the use of training data derived from Landsat imagery in decision tree classifiers. International Journal of Remote Sensing, 19, 3141-3168.
  5. Friedl, M. A., and Brodley, C. E., 1997, Decision tree classification of land cover from remotely sensed data. Remote Sensing of Environment, 61, 399-409.
  6. Gualtieri, J. A., and Cromp, R. F., 1998, Support vector machines for hyperspectral remote sensing classi. cation. In Proceedings of the 27th AIPR Workshop: Advances in Computer Assisted Recognition, Washington, DC, Oct. 27, 1998 (Washington, DC: SPIE), pp. 221-232.
  7. Hall, F. G., Townshend, J. R., and Engman, E. T., 1995, Status of remote sensing algorithms for estimation of land surface state parameters. Remote Sensing of Environment, 51, 138-156.
  8. Hansen, M., DeFries, R. S., Townshend, J. R. G., and Sohlberg, R., 2000, Global land cover classification at 1 km spatial resolution using a classification tree approach. International Journal of Remote Sensing, 21, 1331-1364.
  9. Hansen, M., Dubayah, R., and DeFries, R., 1996, Classification trees: an alternative to traditional land cover classi. ers. International Journal of Remote Sensing, 17, 1075-1081.
  10. Joachims, T., 1998a, Making large scale SVM learning practical. In Advances in Kernel Methods-Support Vector Learning, edited by B. Scholkopf, C. Burges and A. Smola (New York: MIT Press).
  11. Joachims, T., 1998b, Text categorization with support vector machines-learning with many relevant features. In Proceedings of European Conference on Machine L earning, Chemnitz, Germany, April 10, 1998 (Berlin: Springer), pp. 137-142.
  12. Lippman, R. P., 1987, An introduction to computing with neural nets. IEEE ASSP Magazine, 4, 2-22.
  13. Paola, J. D., and Schowengerdt, R. A., 1995, A review and analysis of back propagation neural networks for classi. cation of remotely sensed multi-spectral imagery. International Journal of Remote Sensing, 16, 3033-3058.
  14. Paola, J. D., and Schowengerdt, R. A., 1997, The effect of neural network structure on a multispectral land-use/land cover classification. Photogrammetric Engineering and Remote Sensing, 63, 535-544.
  15. Safavian, S. R., and Landgrebe, D., 1991, A survey of decision tree classifier methodology. IEEE T ransactions on Systems, Man, and Cybernetics, 21, 660-674.
  16. Sellers, P. J., Meeson, B. W., Hall, F. G., Asrar, G., Murphy, R. E., Schiffer, R. A., Bretherton, F. P., et al., 1995, Remote sensing of the land surface for studies of global change: models-algorithms-experiments. Remote Sensing of Environment, 51, 3-26.
  17. Swain, P. H., and Davis, S. M. (editors), 1978, Remote Sensing: the Quantitative Approach (New York: McGraw-Hill).
  18. Townshend, J. R. G., 1984, Agricultural land-cover discrimination using Thematic Mapper spectral bands. International Journal of Remote Sensing, 5, 681-698.
  19. Townshend, J. R. G., 1992, Land cover. International Journal of Remote Sensing, 13, 1319-1328.
  20. Vapnik, V. N., 1995, T he Nature of Statistical L earning T heory (New York: Springer-Verlag).
  21. Vapnik, V. N., 1998, Statistical L earning T heory (New York: Wiley).
  22. Wang, F., 1990, Fuzzy supervised classification of remote sensing images. IEEE Transactions on Geosciences and Remote Sensing, 28, 194-201.
Page 1 of 2
Previous