An efficient unsupervised band selection method based on an autocorrelation matrix for a hyperspectral image

In the field of unsupervised band selection, minimum linear prediction (LP) error is a commonly used criterion function. To avoid the large computational complexity, sequential forward selection (SFS) is often employed for subset search in LP-based methods. In this article, we propose a highly efficient LP-based band selection method termed autocorrelation matrix-based band selection (ACMBS), which adopts the sequential backward selection (SBS) as subset search strategy. Interestingly, the LP error is finally transformed into the inverse of the autocorrelation matrix in ACMBS. Thus the computational complexity of ACMBS is significantly reduced. Moreover, we further improve the accuracy of ACMBS by employing relative error, instead of absolute error, as a cost function which is invariant to the magnitude of bands. The results of the experiment show that ACMBS is quite efficient and outperforms the other compared methods in terms of classification accuracy as well.