2008/4/24 Mike Tintner <[EMAIL PROTECTED]>: > The recurrent, but underlying question in many related discussions here is > whether you, (& Bob & a & linas), think a visual scene - let's say some > people dancing, (real life or in a picture) - can be understood > *geometrically/mathematically,* (by the use of geometric figures and maths > alone). I say it can't, but my impression is that you guys say it can, and > I'd like to be sure of your position. [I am moving on here a little from > the subject of understanding verbal texts, although it's related].
Geometry is a fundamental aspect of most computer vision. The world can only be perceived through a camera or an eye imperfectly and with limited resolution, so that when you analyse collections of pixels features such as lines and angles often don't really exist in the data itself. Instead your mind is superimposing a geometry onto the data as the best possible hypothesis derived from statistical properties of significant numbers of pixels (a prediction which is continually being refined as more data becomes available). Sometimes, as in the surrealist double images, your mind will flip between alternative hypotheses about what is being seen. Geometry allows you to reconstruct visual information which is degraded, damaged, obscured or otherwise ambiguous. Just in case anyone objects that "blind people still have imagination" there does seem to be considerable evidence that spatial awareness is not solely a function of vision (for example http://www.newscientist.com/channel/being-human/mg18524841.700). My parents have a cat who is completely blind and quite deaf, but she is still able to navigate around using a combination of tactile sense and smell. ------------------------------------------- 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=101455710-f059c4 Powered by Listbox: http://www.listbox.com
