Classification of Polarimetric SAR Images Based on Optimum SVMs Classifier Using Bees Algorithm

Because of Polarimetric Synthetic Aperture Radar (PolSAR) contains the different features which relate to the physical properties of the terrain in unique ways, polarimetric imagery provides an efficient tool for the classification of the complex geographical areas. Support Vector Machines (SVMs) are particularly attractive in the remote sensing field due to their ability to handle the nonlinear classifier problem in high dimensional feature space. However, they also suffer from optimum SVMs parameters assignment and optimum feature subset selection issues that can significantly affect on the obtained results. In optimization of SVMs parameters and feature space, traditional optimization algorithms usually trap in local optimum. Thus, it is inevitable to apply meta- heuristic optimization algorithms to obtain global optimum solution. As results, the superior performance of SVMs achieved by simultaneously optimization of SVMs parameters and input feature subset on Polarimetric imagery are demonstrated. This study, initially aims to optimize the accuracy of SVMs classifier by selecting the subset of best informative features and determining the best values for the SVMs parameters. Accordingly, we apply three proposed classification strategies by combining of SVMs classifier and Bees Algorithm. These strategies respectively are; classification based on SVMs parameter optimization, classification based on input feature optimization, and classification based on SVMs parameters and input features optimization. As an experimental result, the potential of three proposed optimization methods for determination of SVMs parameters and feature subset selection based on Bees Algorithm is evaluated and compared with Genetic Algorithm (GA).

[1]  Cheng-Lung Huang,et al.  A GA-based feature selection and parameters optimizationfor support vector machines , 2006, Expert Syst. Appl..

[2]  Jorma Laaksonen,et al.  Detecting changes in polarimetric SAR data with content-based image retrieval , 2007, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[3]  Duc Truong Pham,et al.  Simultaneous Feature Selection and Parameters Optimization for SVM by Immune Clonal Algorithm , 2005, ICNC.

[4]  Wang Yang,et al.  Algorithm of target classification based on target decomposition and support vector machine , 2007, 2007 1st Asian and Pacific Conference on Synthetic Aperture Radar.

[5]  Shih-Wei Lin,et al.  Particle swarm optimization for parameter determination and feature selection of support vector machines , 2008, Expert Syst. Appl..

[6]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[7]  Yanqing Zhang,et al.  A genetic algorithm-based method for feature subset selection , 2008, Soft Comput..

[8]  Jean-Claude Souyris,et al.  Support Vector Machine for Multifrequency SAR Polarimetric Data Classification , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Lamei Zhang,et al.  Polarimetric SAR image classification using Multiple-Component Scattering Model and Support Vector Machine , 2009, 2009 2nd Asian-Pacific Conference on Synthetic Aperture Radar.

[10]  E. Pottier,et al.  Polarimetric Radar Imaging: From Basics to Applications , 2009 .

[11]  Ming-Chi Lee,et al.  Using support vector machine with a hybrid feature selection method to the stock trend prediction , 2009, Expert Syst. Appl..

[12]  Oguz Findik,et al.  A comparison of feature selection models utilizing binary particle swarm optimization and genetic algorithm in determining coronary artery disease using support vector machine , 2010, Expert Syst. Appl..

[13]  E. Colin-Koeniguer,et al.  A review about alternatives to classical Polarimetric SAR parameters , 2010 .

[14]  Jin Zhang,et al.  Optimization of a Subset of Apple Features Based on Modified Particle Swarm Algorithm , 2010, 2010 Third International Symposium on Intelligent Information Technology and Security Informatics.

[15]  Yang Han,et al.  Full polarimetric SAR classification based on Yamaguchi decomposition model and scattering parameters , 2010, 2010 IEEE International Conference on Progress in Informatics and Computing.

[16]  Moncef Gabbouj,et al.  Classification of Polarimetric SAR Images Using Evolutionary RBF Networks , 2010, 2010 20th International Conference on Pattern Recognition.

[17]  Jun Wang,et al.  A real time IDSs based on artificial Bee Colony-support vector machine algorithm , 2010, Third International Workshop on Advanced Computational Intelligence.

[18]  Jose Luis Alvarez-Perez,et al.  Coherence, Polarization, and Statistical Independence in Cloude–Pottier's Radar Polarimetry , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[19]  Jungho Im,et al.  Support vector machines in remote sensing: A review , 2011 .

[20]  Gülsen Taskin Kaya,et al.  Support Vector Selection and Adaptation for Remote Sensing Classification , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[21]  Roman Jarina,et al.  Model parameters selection for SVM classification using Particle Swarm Optimization , 2011, Proceedings of 21st International Conference Radioelektronika 2011.