Recursive spectral similarity measure-based band selection for anomaly detection in hyperspectral imagery

Band selection has been widely used in hyperspectral image processing for dimension reduction. In this paper, a recursive spectral similarity measure-based band selection (RSSM-BBS) method is presented. Unlike most of the existing image-based band selection techniques, it is for two hyperspectral signatures with its main focus on their spectral separability. Furthermore, it is unsupervised and based on the recursive calculation of the spectral similarity measure with an additional band. In order to demonstrate the utility of the proposed method, an anomaly detection algorithm is developed, which first extracts the anomalous target spectrum from the image using the automatic target detection and classification algorithm (ATDCA), followed by the maximum spectral screening (MSS) to obtain a good estimate of the background, and then implements RSSM-BBS to select bands that participate in the subsequent adaptive cosine/coherence estimator (ACE) target detection. As shown in the experimental result on the AVIRIS dataset, the detection performance of the ACE has been improved greatly with the bands selected by RSSM-BBS over that using full bands