Suggested R packages for frontier estimation or segmentation of hyperspectral images An hyperspectral image is a multidimensional image with more than 200 spectral bands i.e. an image for which each pixel is a vector of dimension 200 (most often it is a sampled spectral curve that is encoutered in satellite imagery or medical imagery). 
What are the implemented package (I am especially interested in R packages but if other free algorithms exist, I will try them) for frontier detection and (unsupervised) segmentation of this type of images?  
 A: Not an R package, but D. A. Landgrebe from Purdue (author of Signal theory methods in multispectral remote sensing) has sponsored the MultiSpec freeware.  Its a rather clunky GUI but gets the job done for most of the common hyperspectral algorithms.
A: I am afraid there is no; during my little adventure with such data we have just converted it to a data frame form, added some extra attributes made from neighborhoods of pixels and used standard methods. Still, packages ripa and hyperSpec might be useful.
For other software, I've got an impression that most of sensible applications are commercial.
A: The best place to look for free/open source capabilities of this nature is GRASS GIS.  The image processing manual is here.  Because this is constantly undergoing development, it would be worthwhile posting an inquiry on one of the GRASS user lists (found through links on the home page here.
A: This is a very late response, so this may no longer be of interest, but I am working on putting together an R library with various hyperspectral image processing capabilities. At the moment my focus has been on endmember detection and unmixing. If this is still something which is of interest please let me know. My hope is to publish a beta version to CRAN or R-Forge in the near future but I would be happy to send out the code itself.
Best,
Dan
