CAD/CAM programs (and many others) allow the fairly simple input of complex
objects like the car in your image and can then create an image of the
described object from any view and distance and have done so for years.
The problems are in object isolation (what your first URL dealt with) and in
the initial recognition of *which* object you are attempting to match. It
is not that difficult to determine a match if you are given an object and a
CAD/CAM description.
Defining object variations in CAD/CAM format is also not that tough.
I don't get why you absolutely reject modeling and believe that it's all
done visually.
----- Original Message -----
From: "Mike Tintner" <[EMAIL PROTECTED]>
To: <[email protected]>
Sent: Tuesday, May 27, 2008 5:03 PM
Subject: [agi] Computer Vision May Not Be As Good As Thought
The article below demonstrates my point in the Pattern Definition thread
re the extreme difficulty (I would say: impossibility) of reducing the
variations in an Object Form to Geometric Form(ulae) - and provides a
particularly useful visual illustration. If anyone knows of similar
illustrations, I would be grateful:
http://www.sciencedaily.com/releases/2008/01/080124233657.htm
http://www.sciencedaily.com/images/2008/01/080124233657.jpg
-------------------------------------------
agi
Archives: http://www.listbox.com/member/archive/303/=now
RSS Feed: http://www.listbox.com/member/archive/rss/303/
Modify Your Subscription:
http://www.listbox.com/member/?&;
Powered by Listbox: http://www.listbox.com
-------------------------------------------
agi
Archives: http://www.listbox.com/member/archive/303/=now
RSS Feed: http://www.listbox.com/member/archive/rss/303/
Modify Your Subscription:
http://www.listbox.com/member/?member_id=8660244&id_secret=103754539-40ed26
Powered by Listbox: http://www.listbox.com
