The paper uses some of digital character of spectral curve to describe its configuration character in hyperspectral image. The judging for similarity of spectral curve is transformed the identifying digital character of spectral curve in order to identify pixel similarity, and then hyperspectral image segmentation is carried out. The main characteristics is extracted as follows: the number of wave crest which is above mean, the number of wave valley which is above mean, the number of wave crest which is below mean, the number of wave valley which is below mean, the number of uptrend bands, the number of downtrend bands, the band number of crest, and the band number of valley. The characteristics of spectral curve can not only describe the spectral curve effectively and identify the differences between pixels, but also significantly reduce the computation and improve the efficiency follow-up to deal with. The experiment validates the method.
- Hyper-spectral curve configuration digital character
- Image processing
- Image segmentation
- Remote sensing
ASJC Scopus subject areas
- Electronic, Optical and Magnetic Materials
- Atomic and Molecular Physics, and Optics