Hyperspectral Image Classification Using Kernel Fukunaga-Koontz Transform

This paper presents a novel approach for the hyperspectral imagery (HSI) classification problem, using Kernel Fukunaga-Koontz Transform (K-FKT). The Kernel based Fukunaga-Koontz Transform offers higher performance for classification problems due to its ability to solve nonlinear data distributions. K-FKT is realized in two stages: training and testing. In the training stage, unlike classical FKT, samples are relocated to the higher dimensional kernel space to obtain a transformation from non-linear distributed data to linear form. This provides a more efficient solution to hyperspectral data classification. The second stage, testing, is accomplished by employing the Fukunaga- Koontz Transformation operator to find out the classes of the real world hyperspectral images. In experiment section, the improved performance of HSI classification technique, K-FKT, has been tested comparing other methods such as the classical FKT and three types of support vector machines (SVMs).

[1]  Wenming Zheng,et al.  A new discriminant subspace analysis approach for multi-class problems , 2012, Pattern Recognit..

[2]  Mark R. Pickering,et al.  Unsupervised band removal leading to improved classification accuracy of hyperspectral images , 2006, ACSC.

[3]  M. Kalacska,et al.  Using police seizure data and hyperspectral imagery to estimate the size of an outdoor cannabis industry , 2011 .

[4]  Keinosuke Fukunaga,et al.  Application of the Karhunen-Loève Expansion to Feature Selection and Ordering , 1970, IEEE Trans. Computers.

[5]  Marios Savvides,et al.  Kernel Fukunaga-Koontz Transform Subspaces For Enhanced Face Recognition , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Gustavo Camps-Valls,et al.  Urban Image Classification With Semisupervised Multiscale Cluster Kernels , 2011, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[7]  Atsushi Kume,et al.  Remote sensing of vegetation , 2014 .

[8]  Bruce J. Tromberg,et al.  Face Recognition in Hyperspectral Images , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  José M. Bioucas-Dias,et al.  Bayesian Hyperspectral Image Segmentation With Discriminative Class Learning , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Gary A. Shaw,et al.  Hyperspectral Image Processing for Automatic Target Detection Applications , 2003 .

[11]  Ruiming Liu,et al.  Infrared Point Target Detection with Fisher Linear Discriminant and Kernel Fisher Linear Discriminant , 2010 .

[12]  Abdullah Bal,et al.  Fukunaga-Koontz transform based dimensionality reduction for hyperspectral imagery , 2006, SPIE Defense + Commercial Sensing.

[13]  Filiberto Pla,et al.  Textural Features for Hyperspectral Pixel Classification , 2009, IbPRIA.

[14]  David Zhang,et al.  Classification of hyperspectral medical tongue images for tongue diagnosis , 2007, Comput. Medical Imaging Graph..

[15]  Johannes R. Sveinsson,et al.  Classification of hyperspectral data from urban areas based on extended morphological profiles , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[16]  Saurabh Prasad,et al.  Automated hyperspectral imagery analysis via support vector machines based multi-classifier system with non-uniform random feature selection , 2011, 2011 IEEE International Geoscience and Remote Sensing Symposium.

[17]  M. N. Islam,et al.  Hyperspectral target detection using Gaussian filter and post-processing , 2008 .