Input Textural Feature Selection By Mutual Information For Multispectral Image Classification

Texture information plays increasingly an important role in remotely sensed imagery classification and many pattern recognition applications. However, the selection of relevant textural features to improve this classification accuracy is not a straightforward task. This work investigates the effectiveness of two Mutual Information Feature Selector (MIFS) algorithms to select salient textural features that contain highly discriminatory information for multispectral imagery classification. The input candidate features are extracted from a SPOT High Resolution Visible(HRV) image using Wavelet Transform (WT) at levels (l = 1,2). The experimental results show that the selected textural features according to MIFS algorithms make the largest contribution to improve the classification accuracy than classical approaches such as Principal Components Analysis (PCA) and Linear Discriminant Analysis (LDA).

Authors:

• Mounir Ait kerroum
• Ahmed Hammouch
• Driss Aboutajdine

Keywords:

• Feature Selection
• Texture
• Mutual Information
• Wavelet Transform
• SVM classification
• SPOT Imagery.

References:

[1] T. M. Cover and J. A. Thomas, Elements of Information Theory, 2nd ed.
Jhon Wiley, 2006.
[2] C. E. Shannon and W. Weaver, The Mathematical Theory of Communication,
Univ. Illinois Press, Urbana, 1949.
[3] R. Battiti, Using Mutual Information for Selecting Features in Supervised
Neural Net Learning, IEEE Transactions on Neural Networks. Vol 5 NO
4, july 1994.
[4] N. Kwak and C. H. Choi, Input Feature Selection for Classification
Problems, IEEE Transactions on Neural Networks, pp. 143-159, january,
2002.
[5] J. Huang, Y. Cai and X. Xiaoming, A Wrapper for Feature Selection
Based on Mutual Information, 18th International Conference on Pattern
Recognition, ICPR-06, Volume 2, 2006.
[6] H. Peng, F. Long and C. Ding, Feature Selection Based on Mutual Informtion:
Criteria of Max-Dependency, Max-Relevance and Min-redundancy,
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.
27. NO 8. August, 2005.
[7] C. Ding and H.C. Peng, Minimum Redundancy Feature Selection from
Microcarray Gene Expression Data, second IEEE Computational Systems
Bioinformatics Conf.,pp. 523-528, August, 2003.
[8] A. J. Richards and Xiuping Jia, Remote Sensing Digital Image Analysis
An Introduction, 4th ed. Springer-Verlag, 2006.
[9] M. Ait kerroum, A. Hammouch and D. Aboutajdine, Textural Feature
Selection Based on Mutual Information, second International Symposium
on Communications, Control and Signal Processing ISCCP, Marrakech,
Morocco, 2006.
[10] A. Hammouch, D. Aboutajdine and J. M. Boucher, Evaluation comparative
en cartographie foresti`ere de l-analyse de texture et de la transform'ee
en paquets d-ondelettes par le moyen d-un classifieur neuronal, Revue
Photo-interprtation, N 2004/1, 2004.
[11] N. Kwak and C. H. Choi, Input Feature Selection by Mutual Information
Based on Parzen Window, IEEE Trans. on pattern analysis and Machine
Intellligence, vol 24, no 12, pp.1065-1076, December, 2002.
[12] W.K. Pratt, Digital Image Processing, 3rd ed. Jhon Wiley, New York,
2001.
[13] X. Tang and W. K. Stewart, Optical and Sonar Image Classification:
Wavelet Packet Transform vs. Fourier Transform, Computer vision and
image understanding, vol. 79, pp. 25-46, August, 2000.
[14] K. Torkkola, Feature Extraction by Non-Parametric Mutual Information
Maximization, Journal of Machine Learning Research, pp. 1415-1438,
marsh, 2003.
[15] N. Kwak and C.H. Choi, Improved Mutual Information Feature Selector
for Neural Networks in Supervised Learning, Int. Joint Conf. on Neural
Networks, Washington D.C., July, 1999.
[16] K. Fukunaga, Introduction to Statistical Pattern Recogntion, 2nd. ed.
1990.
[17] V. Vapnik, Statistical Learning Theory, Wiley, New York, 1998.
[18] M. Ait Kerroum, A. Hammouch and D. Aboutajdine, Using The
Maximum Mutual Information Criterion to Textural Feature Selection
For Satellite Image Classification, The Thirteenth IEEE Symposium on
Computers and Communications ISCC-08, Marrakech, Morocco, July,
2008.
[19] V. Vapnik, Estimation of Dependencies Based on Data, Springer-Verlag,
Trans. Moscow: Nauka, 1979.
[20] V. Vapnik, The Nature of Statistical Learning Theory, Berlin: Springer-
Verlag, 1995.
[21] http://www.csie.ntu.edu.tw/ cjlin/libsvm
[22] S.T. Bow, Pattern Recognition and Image Processing, 2nd. ed. 2002.