Kernel based Multi-Class Classification of Satellite Images with RVM Classifier using Wavelet Transform

Multispectral satellite images are more efficient and a suitable method of obtaining information about land, because it can captures an image at specific frequency across the spectrum. This spectral image can allow extraction of further information about ground survey than the other traditional image. Classification of multispectral image consists of image processing and classification method. Here, an efficient technique is proposed for classifying the multispectral images using fuzzy incorporated hierarchical clustering with RVM classifier. In the proposed technique, first the multispectral satellite image is subjected to set of pre-processing steps, which are used to transform an image into suitable form that is easier for segmentation and classification. Subsequently, the pre-processed image is segmented using fuzzy incorporated hierarchical clustering. Then, the proper kernel function is selected for RVM clustered output. Finally the multispectral image is classified into multiple sectors based on the training data. The classification is used in the application of land degradation studies, environmental damage, resource management and other environmental application.

[1]  Sheng Chen,et al.  The relevance vector machine technique for channel equalization application , 2001, IEEE Trans. Neural Networks.

[2]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[3]  Giles M. Foody,et al.  Evaluation of SVM, RVM and SMLR for Accurate Image Classification With Limited Ground Data , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[4]  M. Archana,et al.  Human Behavior Classification Using Multi-Class Relevance Vector Machine , 2010 .

[5]  Jon Atli Benediktsson,et al.  Evaluation of Kernels for Multiclass Classification of Hyperspectral Remote Sensing Data , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[6]  M. Ohsaki,et al.  Comparison between Minimum Classification Error training and Relevance Vector Machine , 2012, TENCON 2012 IEEE Region 10 Conference.

[7]  Fangting Sun,et al.  A hierarchical image segmentation algorithm , 2002, Proceedings. IEEE International Conference on Multimedia and Expo.

[8]  Bo Huang,et al.  Land-Use-Change Modeling Using Unbalanced Support-Vector Machines , 2009 .

[9]  Ye Zhang,et al.  Nonlinear discriminant analysis and RVM for efficient classification of small land-cover patches , 2011, 2011 International Conference on Communications and Signal Processing.

[10]  Ye Zhang,et al.  Robust Hyperspectral Classification Using Relevance Vector Machine , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[11]  Begüm Demir,et al.  Hyperspectral Image Classification Using Relevance Vector Machines , 2007, IEEE Geoscience and Remote Sensing Letters.

[12]  Qihao Weng,et al.  A survey of image classification methods and techniques for improving classification performance , 2007 .

[13]  Michael E. Tipping.  The Relevance Vector Machine , 1999, NIPS.

[14]  Alireza Bayestehtashk,et al.  Target Tracking Using Wavelet Features and RVM Classifier , 2008, 2008 Fourth International Conference on Natural Computation.

[15]  Pilar Carrión,et al.  Classification of honeybee pollen using a multiscale texture filtering scheme , 2004, Machine Vision and Applications.

[16]  Lorenzo Bruzzone,et al.  Kernel-based methods for hyperspectral image classification , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Qingsong Xu,et al.  Rate-Dependent Hysteresis Modeling and Control of a Piezostage Using Online Support Vector Machine and Relevance Vector Machine , 2012, IEEE Transactions on Industrial Electronics.

[18]  Amir B. Geva,et al.  Hierarchical unsupervised fuzzy clustering , 1999, IEEE Trans. Fuzzy Syst..

[19]  B. Sowmya,et al.  Land cover classification using reformed fuzzy C-means , 2011 .

[20]  Dong-Hyuk Shin,et al.  Block-based noise estimation using adaptive Gaussian filtering , 2005, IEEE Transactions on Consumer Electronics.

[21]  Shaomei Yang,et al.  Research on Comparison and Application of SVM and FNN Algorithm , 2008, 2008 4th International Conference on Wireless Communications, Networking and Mobile Computing.

[22]  Uwe Weidner,et al.  Classification in High-Dimensional Feature Spaces—Assessment Using SVM, IVM and RVM With Focus on Simulated EnMAP Data , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[23]  Gang Wang,et al.  A regularization framework for multiclass classification: A deterministic annealing approach , 2010, Pattern Recognit..

[24]  Dongmei Chen,et al.  Wavelet-Based Classification of Remotely Sensed Images: A Comparative Study of Different Feature Sets in an Urban Environment , 2007 .

[25]  Wassim M. Haddad,et al.  Relevance Vector Machine Learning for Neonate Pain Intensity Assessment Using Digital Imaging , 2010, IEEE Transactions on Biomedical Engineering.