Application of the Second-Order Statistics for Estimation of the Pure Spectra of Individual Components from the Visible Hyperspectral Images of Their Mixture
This work addresses a specific issue in hyperspectral imaging for chemical analysis, but it is incremental as it builds on existing SOS methods.
The paper tackled the problem of estimating pure spectra from mixtures using second-order statistics, which sometimes produce opposite peak directions; they proposed a method using histograms to determine peak direction, resulting in reasonable shapes and directions for two- and three-component mixtures.
The second-order statistics (SOS) can be applied in estimation of the pure spectra of chemical components from the spectrum of their mixture, when SOS seems to be good at estimation of spectral patterns, but their peak directions are opposite in some cases. In this paper, one method for judgment of the peak direction of the pure spectra was proposed, where the base line of the pure spectra was drawn by using their histograms and the peak directions were chosen so as to make all of the pure spectra located upwards over the base line. Results of the SOS analysis on the visible hyperspectral images of the mixture composed of two or three chemical components showed that the present method offered the reasonable shape and direction of the pure spectra of its components.