2008/8/14 Mike Tintner <[EMAIL PROTECTED]>:
> What it comes down to is: what can you learn about any object[s] from flat
> drawings of them? Cardboard cutouts?


This is essentially the same problem as in computer vision.  The
objects that you're looking at are three dimensional, but a camera
image is only a two dimensional shadow of them.  The problem then
becomes one of trying to reverse engineer the 3D shape from a set of
lower dimensional shadows.  Many researchers in computational vision
forget about this and try to directly scrape information exclusively
in 2D.  For objects which are flat, such as a painting or the cover of
a book, this approach works well (see the vision systems from
evolution robotics and skilligent) but on things which have
significant 3D structure performance usually degrades significantly.


-------------------------------------------
agi
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=8660244&id_secret=111637683-c8fa51
Powered by Listbox: http://www.listbox.com

Reply via email to