John, I welcome you or anyone else replying, but you're essentially saying "It can be done" without offering any recognition of the problem, or any attempt at targeting a solution, just in the end blind faith - "give it enough bandwidth and there'll be an algorithmic solution."
Perhaps the problem needs to be formulated schematically/near-geometrically for you to see and acknowledge it - i.e. reduce those fotos to their outlines - I haven't got time now but I might do it later. The problem is that a) any object can take a virtually infinite variety of shapes according to POV, position, lighting, colouring and intermediate objects . And b) the great majority of objects are irregular - like a human face - and don't have an intrinsic formula or pattern to them anyway. So you have to offer just the teeniest bit of an idea of how you're going to establish a formula - of whatever kind, including algorithmic - for recognizing the vast variety of transformations an object - even a simple object - can be subjected to. If you want an almost pure "geometric" formulation of the problem, tell me how you are going to recognize a "doodle." None of you mathematicos had any suggestions as to how a single doodle that I provided months ago could be geometrical/algorithmic. So how on earth are you going to recognize the extraordinary variety of "doodle"s that humans draw? And yet humans are highly successful in recognizing them. [This is an extreme version of the problem, but its advantage lies, as I said, in its near-geometric, highly linear nature - and, as a mathematician, I think you should welcome it]. It can all be done - and done mechanically - but not, I think, by any of the means currently being used. John GR: Mike, It's not all "geometric". Patterns need not be defined by vector' lines, or only magnitudes of image properties. The same recognition mechanisms in the brain are emulatable by mathematical, indexable, categorizable, recognizable and systematic, engineered processes. Even images of Madonna- which it's nice to whip out more complex(complicated) examples to entice refutement - you should start off with simpler and then move to complex a.k.a. engineering verses philosophy. But building up a pattern recognizer is not something that is formidable, it's just work that needs to be done. I don't see problems here even with complex imagery, video it's just resources. Sure some algorithms need to be refined and an AGI algorithm verses standard pattern recognition hardcoded- the same algorithms should be applicable to visual, audial, language - over a diverse set of I/O streams. john From: Mike Tintner [mailto:[EMAIL PROTECTED] Sent: Tuesday, May 13, 2008 4:01 PM To: agi@v2.listbox.com Subject: Re: [agi] Re: pattern definition Joe, Thanks for reply - yes, I thought you meant something like this, but it's good to have it spelled out. I think you're making what seems to me to be a v. common mistake among AGI-ers. Yes, you can reduce any image whatsoever on a computer screen, to some set of mathemetical formulae/properties. You can reduce it to so many lines, points, triangles, fractals etc. etc But that's not the problem. The problem is: how do you do that *systematically* for a SET of images (not just one)? How can you guarantee (or come anywhere remotely close) that your system of GEOMETRIC FORM analysis will be able to recognize the same OBJECT FORMS in many different images? - that by breaking complex images down into all those lines, points etc in whatever way you choose, you will be able to recognize, say, the faces, noses, mouths, necks etc in several, different images? Or the plastic bags in them? To focus the problem - in admittedly a v. difficult form (but hopefully it will help you focus better) - how will your *geometric* system recognize the faces and their parts in this set of images, as humans can: http://cr.middlebury.edu/public/spanish/sp371/images/esperpento/goya_viejos.jpg http://www.thebestlinks.com/images/2/2f/El_Greco.jpg http://www.nzine.co.nz/images/articles/picasso_lg.jpg http://www.roussard.com/media/oeuvres/modigliani/lithos/modiglianiIMGP6719.jpg http://www.gerard-schurmann.com/bacon.jpg http://aphrabehn.files.wordpress.com/2007/03/scarfe1.jpg http://www.oppdalfilmklubb.no/img/the-wall.jpg http://www.frederickwildman.com/wildmansite/wmphp/images/hugel/10large.jpg http://internat.martinique.free.fr/images/le_sommeil-salvador_dali.jpg (Note that even a set of ordinarily photographed faces in different positions will still present all kinds of recognition problems). How IOW do you equate an OBJECT FORM like that of face/ nose/ mouth/ chair/ tree/ oak/ handbag etc. etc. with GEOMETRIC FORMS? I am pretty sure that no such equation is possible, period - given that objects can take a vast if not infinite range of forms from different POV's.and in different positions. And that surely is what the history of failures in visual object recognition tells us. (What BTW is *your* explanation of that history of failure? It is rather surprising (no?) that so many AGI-ers can state that images can definitely be analysed geometrically, given the field's striking lack of success here. Surely a certain amount of questioning and soul-or-some-part-of-brain-searching is in order here). I think it's worth thrashing this subject out, because it keeps cropping up here and elsewhere and is so important - and you seem like a reasonable guy, so maybe we (& anyone else) can do that. I think my distinction between geometric form and object form is v. helpful for discussions here, & it may not be at all new, but it doesn't seem to be commonplace. P.S. Yes, bucket is a simple object - and it's conceivable that a lot of people might come up with similar mental visualisations of the concept - but even then you might be surprised - and McLuhan's point was re WORD descriptions of buckets and other objects. If you think you can describe it or almost any other object verbally, be my guest :). Even recognising the buckets in different images - (and therefore developing a viable equation of bucket with geometric forms) - strikes me as no simple task for a computer: http://classroomclipart.com/images/gallery/New/Clipart3/paint_brush.jpg http://www.craftamerica.com/images/products/6500_75_rusty_tin_bucket.jpg http://christopher-pelley.abbozzogallery.com/images/red%20bucket.jpg http://www1.istockphoto.com/file_thumbview_approve/487639/2/istockphoto_487639_bucket_and_spade.jpg http://z.about.com/d/hotels/1/0/l/G/bucket.jpg http://www.bobjonespaintings.com/large%20images/bucket.jpg http://www.jenklairkids.com/Eshop/products/girl_dog_bucket.jpg http://annievic.accountsupport.com/images/beachrosebucket.jpg http://www.entretienardiz.com/images/cleaning_bucket.jpg Well, I figured the point of the question would be pretty clear seeing as you were claiming a logical/mathematical description of images would be inadequate, but I don't think that could be further from the truth... You could recreate a large amount of detail in an image using mathematics and it would be a great deal more compact of a description than a bitmap representation. AND, you could store the mathematical properties of the image in a DB of some sort to find similar shapes within a large body of images. When you remember scenes from years ago, it is unlikely that you remember which way the grain of the wood was facing, or how many scratches were on the left side of a corner table's handle... so why not represent them in a similar manner as vector images? Using a mathematical description would allow for a more compact, searchable, and inference-available representation. To me, keeping a little box of mathematical expressions to describe an image is a far better choice of both memory and potential processing power than to lug around a bitmap or any sort, unless you want to store the image in case you find another way to interpret it. Though humans don't remember everyday scenes through mathematical description, we do prune out the irrelevant stuff by only remembering general shapes, common textures, and orientations (unless we make it a priority to remember specific features). Mathematical equations and logical statements might not tell YOU a lot about an image, but if someone were to sit down and carefully describe an image using logical statements, equalities, and mathematical expressions, and if someone were to sit down and carefully read these... with time the image would emerge, though we humans aren't suited for this task, a machine will be more than capable, and it would be a much wiser use of resources. - Joe ---------------------------------------------------------------------------- agi | Archives | Modify Your Subscription ------------------------------------------------------------------------------ agi | Archives | Modify Your Subscription ------------------------------------------------------------------------------ agi | Archives | Modify Your Subscription ------------------------------------------- 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
