- Create hyperspectral signatures either by convolution of library spectral curves or by supervised signature extraction.
- Automatically develop signatures for hyperspectral image data based on the linear spectral unmixing logic.
- Deselect high noise bands from a hyperspectral series based on an autocorrelation threshold.
- Spectral Angle Mapper classifier for hyperspectral data.
- Minimum distance to means hyperspectral classifier that accounts for illumination effects.
- Unsupervised classification for hyperspectral image data.
- Hyperspectral image classification through an orthogonal subspace projection approach.
- Linear spectral unmixing for hyperspectral data.
- Hyperspectral image classification based on library spectra and continuum removal of absorption areas and the correlation of these areas in terms of fit and depth between the library spectrum and the spectra from an imaging data set.
 |
|
| Techniques for hyperspectral image analysis are available in IDRISI. Available tools include absorption spectra analysis using continuum removal for estimation of the degree of support for members of a library of spectral response curves developed in a laboratory setting, an unsupervised classifier, and several supervised classifiers including orthogonal subspace projection and linear spectral unmixing.
| |  |
|
;)
