MTMF MTMF combines the best parts of the Linear Spectral Mixing model and the statistical Matched Filter model while avoiding the drawbacks of each parent method (Boardman, 1998). It is a useful Matched Filter method without knowing all the possible endmembers in a landscape especially in case of subtle, sub-pixel occurrences. Firstly, pixel spectra and endmember spectra require a minimum noise fraction (MNF) (Green et al., 1988, Boardman, 1993) transformation. MNF reduces and separates an image into its most dimensional and non-noisy components. Once the data is in a less noisy form, it can then be compared to endmember through MTMF processes to determine composition. Its results. | Data Mining and Knowledge Discovery IN Real Life Applications Data Mining AND KNOWLEDGE Discovery in Real Life Applications Edited By Julio PũNCE and Adem Karahoca .
