Band Selection for Hyperspectral Image Classification Using Mutual Information

• Published in: IEEE geoscience and remote sensing letters Vol. 3; no. 4; pp. 522 - 526
• Main Authors: Baofeng Guo, Gunn, S.R., Damper, R.I., Nelson, J.D.B.
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.10.2006; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Bands; Classification; Computational efficiency; Data processing; Ground truth; Gunn devices; Hyperspectral imaging; Hyperspectral sensors; Image classification; Image databases; image region classification; Layout; Mutual information; Random variables; remote sensing; spectral band selection; Spectral bands; Strategy; support vector machines (SVMs)
• ISSN: 1545-598X; 1558-0571
• DOI: 10.1109/LGRS.2006.878240

Spectral band selection is a fundamental problem in hyperspectral data processing. In this letter, a new band-selection method based on mutual information (MI) is proposed. MI measures the statistical dependence between two random variables and can therefore be used to evaluate the relative utility of each band to classification. A new strategy is described to estimate the MI using a priori knowledge of the scene, reducing reliance on a "ground truth" reference map, by retaining bands with high associated MI values (subject to the so-called "complementary" conditions). Simulations of classification performance on 16 classes of vegetation from the AVIRIS 92AV3C data set show the effectiveness of the method, which outperforms an MI-based method using the associated reference map, an entropy-based method, and a correlation-based method. It is also competitive with the steepest ascent algorithm at much lower computational cost