Hyperspectral Images Terrain Classification Based on Power Transformation


Article Preview

In order to make the class distribution be close to Gaussian distribution, a hyperspectral images terrain classification method is presented base on power transformation (PT). Firstly PT is performed to original hyperspectral data to improve the class distribution Gaussianity, and then direct linear discriminant analysis (dLDA) is used to extract features, finally Bayesian classifier is designed in the achieved feature subspace for recognition. Experimental results based on airborne visible/infrared imaging spectrometer (AVIRIS) hyperspectral image show that, with data power transformed, the recognition rate of Bayesian classifier is dramatically improved, and the feature extraction effect of dLDA is enhanced to a certain degree.



Edited by:

Zhengyi Jiang, Yugui Li, Xiaoping Zhang, Jianmei Wang and Wenquan Sun




J. Liu and Y. Liu, "Hyperspectral Images Terrain Classification Based on Power Transformation", Applied Mechanics and Materials, Vols. 220-223, pp. 2886-2890, 2012

Online since:

November 2012





[1] T.V. Bandos, L. Bruzzone and G. Camps-Valls: IEEE Trans. Geosci. Remote Sens. Vol. 47 (2009), p.862.

[2] W. Li, S. Prasad, J.E. Fowler and L.M. Bruce: IEEE Geosci. Remote Sens. Letters Vol. 8 (2011), p.894.

[3] Q. Du and N.H. Younan: Lect. Note Comput. Sci. Vol. 5179 (2008), p.392.

[4] P.F. Hsieh, D.S. Wang and C.W. Hsu: IEEE Trans. Pattern Anal. Mach. Intell. Vol. 28 (2006), p.223.

[5] C.H. Chen and P.G.P. Ho: Pattern Recognition Vol. 41 (2008), p.2731.

[6] J.A. Richards and X.P. Jia: Remote Sensing Digital Image Analysis: An Introduction (Springer-Verlag, Germany 2006).

[7] M.M. Dundar and D.A. Landgrebe: IEEE Trans. Geosci. Remote Sens. Vol. 42 (2004), p.271.

[8] G.E.P. Box and D.R. Cox: J. R. Stat. Soc. B Vol. 26 (1964), p.211.

[9] R. Van der Heiden and F.C.A. Groen: Pattern Recognition Vol. 30 (1997), p.273.

[10] H. Yu and J. Yang: Pattern Recognition Vol. 34 (2001), p. (2067).