[Nautilus-list] Fwd: Fer de Lance, intelligence for the free desktop

[David Rosky <dave rosky tsc tdk com>]

I also tried the demo posted in the original message and it is
very impressive.

I didn't have time to read all of the information available, so
I'm not quite sure how it works, but it already works well for
images. If the same algorithms could be adapted to a few
other types of data, this could really be a *killer* feature.

Take music files: It would be really nice, for example, to 
be able to extract all of one's music files that match similarity 
criteria, for example things like all instrumentals (no voice), all 
songs (with voice),  all fast-beat tracks, all classical-like tracks,
all bluegrass tracks, all heavy metal tracks, etc., etc.

You could do a content based search, load the list into XMMS, and
instantly have all of the music that fits your current mood extracted
from all of your different directories.  This would be VERY nice.

-D