spectral classification using adaboost spectral angle mapper for hyperspectral image analysis

초록

In the remote sensing community, the spectral angle mapper (SAM) has been widely used as a spectral similarity measure for material identification. It calculates the angle between two spectra and uses it as a measure of discrimination. In this paper, we proposed an enhanced of SAM classification algorithm using the Adaboost for hyperspectral image analysis. By applying the Adaboost algorithm to the SAM classifier, the classification can be executed iteratively by giving weight to the spectral data, thus will reduce the classification error rate. From the experimental result, the Adaboost SAM classifier increases the average classification accuracy of SAM classifier from 97.2% to 99.8%.