Mike,
Are you serious or do you just like to draw attention to yourself on this list by making outlandish statements? I don't think you understand just how sophistication many visual processing programs are. For example, about ten years ago I heard a presentation at MIT by a grad student who had written a program that would do correspondence mappings between corresponding parts of different views at different scales of the same animal, of different animals of the same type, and of animals of different but roughly similar types, such as between a horse and a giraffe, or even between different models of automobiles. Once you had such a correspondence mapping you could morph one image onto the shape of the other. It is well known how to derive 3-d models of scenes from images at different positions and then to generate interpolated views from positions from which no such images were taken, letting one in effect navigate within the 3d model. There are even programs that can guess the articulation skeleton of flexible objects from observing their motion over time and then map observed motions onto them under software control. There are multiple programs that can recognize shapes such as circles as a "circle" distinct from a bunch of dots (because not all bunches of dots are circles). And they do this without my projecting my consciousness into them. There are programs that can do much more sophisticated forms of visual recognition that that, including programs that use statistics about what types of objects often appear together to use the recognition of one object in an image as being of a given type to alter the probability with which it is likely to recognize other visual patterns in the image as corresponding to different types of objects. I give up on this thread. I think you either don't know much about current AI or you purposely seek to get attention by making bold but largely baseless challenges against the statements of others. Perhaps I am wrong about your motivations and level of knowledge, but the evidence I have seen in this thread and in prior exchanges with you makes me think I am not. Ed Porter -----Original Message----- From: Mike Tintner [mailto:[EMAIL PROTECTED] Sent: Saturday, February 16, 2008 5:14 PM To: [email protected] Subject: Re: [agi] A 1st Step To Using Your Image-ination...p.s. Ed: I agree that computer cannot yet deal with images in all the ways humans can, but contrary to your statement they can handle them, can reshape them, can put them on top of one another to see if they fit, and much more as well. It sounds like you haven't been keeping up with the state of the art in image processing Ed, A further really central question occurs. You might say: "A computer draws a circle (or other shape)." But does it? Doesn't it just execute a function like nr 2? And draw in effect a series of dots? How does it know the difference between a "circle" and a "series of dots/pixels" - at the physical level? Isn't the only one we can say for sure, that sees the shape/circle - you, the programmer/observer? Aren't you actually projecting your consciousness and own internal image processing into its non-existent mind, when you say it draws a shape, or any form? (Richard's v. good on this sort of thing - any comments, Richard?). _____ agi | <http://www.listbox.com/member/archive/303/=now> Archives <http://www.listbox.com/member/archive/rss/303/> | <http://www.listbox.com/member/?&;> Modify Your Subscription <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=95818715-a78a9b Powered by Listbox: http://www.listbox.com
