Proceedings Article | 25 October 2006
Proc. SPIE. 6378, Chemical and Biological Sensors for Industrial and Environmental Monitoring II
KEYWORDS: Signal to noise ratio, Hyperspectral imaging, Minerals, Interference (communication), Image analysis, Image sensors, Calcite, Neodymium, Detection theory, Signal detection
An endmember is an idealized, pure signature for a class and provides crucial information for hyperspectral image
analysis. Recently, endmember extraction has received considerable attention in hyperspectral imaging due to
significantly improved spectral resolution where the likelihood of a hyperspectral image pixel uncovered by a
hyperspectral image sensor as an endmember is substantially increased. Many algorithms have been proposed for this
purpose. One great challenge in endmember extraction is the determination of number of endmembers, <i>p </i>required for an
endmember extraction algorithm (EEA) to generate. Unfortunately, this issue has been overlooked and avoided by
making an empirical assumption without justification. However, it has been shown that an appropriate selection of <i>p</i> is
critical to success in extracting desired endmembers from image data. This paper explores methods available in the
literature that can be used to estimate the value, <i>p</i>. These include the commonly used eigenvalue-based energy method,
An Information criterion (AIC), Minimum Description Length (MDL), Gershgorin radii-based method, Signal Subspace
Estimation (SSE) and Neyman-Pearson detection method in detection theory. In order to evaluate the effectiveness of
these methods, two sets of experiments are conducted for performance analysis. The first set consists of synthetic imagebased
simulations which allow us to evaluate their performance with <i>a</i> <i>priori</i> knowledge, while the second set
comprising of real hyperspectral image experiments which demonstrate utility of these methods in real applications.
