Hyperspectral images often contain hundreds of contiguous spectral bands. MNF allows you to compress this into a handful of "eigenimages" that retain 99% of the useful information.
The first step uses a noise covariance matrix (often estimated from dark current or uniform areas of an image) to "whiten" the noise. This makes the noise variance equal in all bands and uncorrelated between bands. mnf encode
Before training, raw spectral data is transformed into MNF space. Selection: Only the first This makes the noise variance equal in all
Most professional geospatial software, such as ENVI or QGIS , includes built-in tools for performing MNF transforms. In Python, libraries like PySptools or custom implementations using scikit-learn and NumPy are standard for researchers building automated pipelines. such as ENVI or QGIS
Cleaned MNF components provide a more stable foundation for machine learning models, as they eliminate the "noise floor" that can confuse training algorithms. MNF in Machine Learning Pipelines