Mathematical morphology is the non-linear Lattice Theory based construction of image filters. However, multivariate images, such as hyperspectral images, don’t have a total order and existing methods don’t fully exploit the spectral information. Recently supervised orderings were proposed for the definition of a total order in hyperspectral data. In a recent work we proposed the use of Lattice Associative Memories (LAAMs) to build up a supervised ordering. Here we follow that avenue and introduce an absolute LAAM supervised ordering. Supervised ordering rely on the definition of a foreground and background sets of training data points. We propose an automatic methodology to construct the training sets without a-priori information. For that, we make use of endmember induction algorithms. We demonstrate some results on the well known Pavia image.
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
Tel.: +1 703 830 6300
Fax: +1 703 830 2300 email@example.com
(Corporate matters and books only) IOS Press c/o Accucoms US, Inc.
For North America Sales and Customer Service
West Point Commons
Lansdale PA 19446
Tel.: +1 866 855 8967
Fax: +1 215 660 5042 firstname.lastname@example.org