Title :
Determining the Intrinsic Dimension of a Hyperspectral Image Using Random Matrix Theory
Author :
Cawse-Nicholson, K. ; Damelin, S.B. ; Robin, A. ; Sears, M.
Author_Institution :
Sch. of Comput. & Appl. Math., Univ. of the Witwatersrand, Johannesburg, South Africa
Abstract :
Determining the intrinsic dimension of a hyperspectral image is an important step in the spectral unmixing process and under- or overestimation of this number may lead to incorrect unmixing in unsupervised methods. In this paper, we discuss a new method for determining the intrinsic dimension using recent advances in random matrix theory. This method is entirely unsupervised, free from any user-determined parameters and allows spectrally correlated noise in the data. Robustness tests are run on synthetic data, to determine how the results were affected by noise levels, noise variability, noise approximation, and spectral characteristics of the end-members. Success rates are determined for many different synthetic images, and the method is tested on two pairs of real images, namely a Cuprite scene taken from Airborne Visible InfraRed Imaging Spectrometer (AVIRIS) and SpecTIR sensors, and a Lunar Lakes scene taken from AVIRIS and Hyperion, with good results.
Keywords :
geophysical image processing; hyperspectral imaging; lakes; matrix algebra; unsupervised learning; AVIRIS; Cuprite scene; Hyperion; SpecTIR sensors; airborne visible infrared imaging spectrometer; end-member spectral characteristics; hyperspectral image; intrinsic dimension determination; lunar lakes; noise approximation; noise levels; random matrix theory; spectral unmixing process; spectrally correlated noise; synthetic data; unsupervised methods; Approximation algorithms; Covariance matrix; Eigenvalues and eigenfunctions; Hyperspectral imaging; Noise; Vectors; Hyperspectral; intrinsic dimension; linear mixture model; random matrix theory; unmixing;
Journal_Title :
Image Processing, IEEE Transactions on
DOI :
10.1109/TIP.2012.2227765
