Whitens a HSI cube. Use the noise covariance matrix to decorrelate
and rescale the noise in the data (noise whitening).
Results in transformed data in which the noise has unit variance
and no band-to-band correlations.
- Parameters:
- M: numpy array
- 2d matrix of HSI data (N x p).
- Returns: numpy array
- Whitened HSI data (N x p).
- Reference:
- Krizhevsky, Alex, Learning Multiple Layers of Features from
Tiny Images, MSc thesis, University of Toronto, 2009.
See Appendix A.