Hyperspectral image data reduction by optimal band selection is explored. Hyperspectral images have many bands requiring significant computational power for machine interpretation. During image pre- processing, regions of interest that warrant full examination need to be identified quickly. One technique for speeding up the processing is to use only a small subset of bands to determine the 'interesting' regions. The problem addressed here is how to determine the fewest bands required to achieve a specified performance goal for pixel classification. The (m,n) feature selection algorithm of Stearns is used to determine which combination of bands has the smallest probability of pixel misclassification. This technique avoids having to test all the possible combinations of 200 or more hyperspectral bands, while resisting the pitfalls demonstrated by Cover, et al., that fool other band selection algorithms.
展开▼
