Catch up on stories from the past week (and beyond) at the Slashdot story archive

 


Forgot your password?
Close
typodupeerror
×
Technology Science

Using Computers To Weed Out Art Fakes 192

Posted by timothy from the that's-my-impression dept.
jackelfish writes "Reminiscent of handwriting analysis software used in the television series CSI, computers are now being used to evaluate the authenticity of works of art without an expert ever setting eyes on it. The technique identifies the artist by analyzing their characteristic brush or pen strokes from high resolution scans of previously authenticated works. Much like a fingerprint, these characteristics can then be compared to a work in question. The method, to be published in an upcoming issue of the Proceedings of the National Academy of Sciences promises to reduce the subjectivity of art assessments made by human experts."
This discussion has been archived. No new comments can be posted.

Using Computers To Weed Out Art Fakes More

Using Computers To Weed Out Art Fakes

Comments Filter:
  • Great... now thanks to CSI we will surely know if Picasso killed Colonel Mustard in the Dining Room with the Candlestick.

    ..ducks.
    • And, while we're at it, if video killed the radio star...

    • Fake Picasso story (Score:5, Funny)

      by commodoresloat ( 172735 ) on Wednesday November 24, 2004 @03:01AM (#10907329)
      I can't remember where I heard this story or if there is any truth to it, but I don't care. Apparently some major art buyer picked up a bunch of picassos and wanted to separate the real from the fake. Since he didn't have a computer that would do it he went to Picasso himself and asked him to go through them for him and let him know which ones were true Picassos. So Picasso puts the paintings in two piles, real and fake. The buyer watches the artist do this for a while and then suddenly stops him as he's putting one in the fake pile and says, "That's not fake; I just bought that from you yesterday; I saw you finish painting it myself!" Picasso looks him in the eye, slightly offended, and says, "I can fake a Picasso as well as anyone else out there."

  • This is an art nerd joke - Laugh (Score:3, Funny)

    by skazatmebaby ( 110364 ) on Wednesday November 24, 2004 @02:07AM (#10907109) Homepage
    Boy!

    Now we'll *finally* know if that Sol Lewitt I have in the living room is legitimate!

    Will the next version work on Film Stills? I have a few Cindy Shermans I'm not too sure about...

    And, so wait, does that mean that the Sherrie Levines that come out as copies are real Sherrie Levines???

  • They've got it backwards (Score:5, Interesting)

    by Dancin_Santa ( 265275 ) <DancinSanta@gmail.com> on Wednesday November 24, 2004 @02:08AM (#10907115) Journal
    Extrapolate all that data about each artist's technique, then turn around and paint a bunch of "authentic" art "authored" by those masters.

    They already have "pencil sketch", "charcoal sketch", and "regular photo" settings at the picture booths down at your local mall. It's just a matter of running a filter over an original image and reproducing the image with the desired effects.

    If they have the filter database built for each master, how hard would it be to have it Markov chain an image with that data?

    This seems like the wrong direction if they want to authenticate images.
    • Extrapolate all that data about each artist's technique, then turn around and paint a bunch of "authentic" art "authored" by those masters.

      This is basically what the best art forgers already attempt to do. Give it a try if you think it's easy.

      They already have "pencil sketch", "charcoal sketch", and "regular photo" settings at the picture booths down at your local mall. It's just a matter of running a filter over an original image and reproducing the image with the desired effects.

      And how do you apply

    • Extrapolate all that data about each artist's technique, then turn around and paint a bunch of "authentic" art "authored" by those masters.

      And just how will you exactly re-create that technique? The fact that humans cannot (currently) do so is exactly why this analysis will work. (When we get robots with hyper fine control, and the AI to prevent each and every brushstroke from being either identical or part of a pattern, this will change.)

      This seems like the wrong direction if they want to authentica

      • Re:They've got it backwards (Score:5, Interesting)

        by SerpentMage ( 13390 ) on Wednesday November 24, 2004 @03:35AM (#10907419)
        No this wont work... What it will do is give a false sense of security. Recently on Discovery Channel Europe they ran a set of documentaries about art theft and art forgery.

        The problem with art forgery is that there are some REALLY good forgers. The one that they interviewed could produce "original" pieces of art in the name of the original artist. The people who were to supposed to catch his forgeries could not because he was that good.

        When they interviewed this Dutch forger he actually studied, and set himself in the frame of mind of the artist. EG he had a Picasso room with Picasso paint brushes, paints, etc. What was brilliant about him is that he was like an actor. You know how an actor does a role play and makes themself become the person. With someone who is that clever all that the computer analysis will do is make his work legit! And that is a bigger problem!

        • Re:They've got it backwards (Score:5, Interesting)

          by HyperCash ( 768512 ) on Wednesday November 24, 2004 @04:51AM (#10907593)
          To me the really good forgers make a mockery of the entire "art crowd" for showing it to be the farce that it is. I mean, if you can't tell the difference between the forgers piece and Picasso's then really, whats the difference? If the foremost experts in the field can't tell the difference the forger's work is just as good. The only difference is branding. Amazing that people will pay hundreds of millions for that.

          --HC

          • Re:They've got it backwards (Score:5, Insightful)

            by cmcguffin ( 156798 ) on Wednesday November 24, 2004 @07:42AM (#10907970)
            It's a question of art history, not a question of "just as good".

            A mediocre work by, say, Picasso, is interesting because it tells a story about his development as an artist, and therefore will likely have some monetary value to a collector or a museum. A mediocre work by, say, me, is just mediocre.

            Museums don't exist just to show "good" pictures. Part of their mission is to preserve and illuminate the history of art.

            Think of it this way: an early, buggy version of linux is interesting from a historical perspective, while an early, buggy version of my personal operating system is of little interesting to anybody.
            • Mod parent up....

              Many now famous artists were not appreciated for what they accomplished in their lifetimes.

              If I studied Greek history, art, and drama for decades and passed a contemperary "Greek Tragedy" off as an ancient work, that derivative work would provide no NEW insight into Greek culture or history. It would at best provide a view into my interpretation and understanding an art form from that time.

          • The main difference is that thiers is a copy verses the original work.
            As for the high prices for original works that is just supply and demand for a rare single item. I have some cheap,but good, posters of Monet but would love to have originals, so would alot of others who have more spendable money then I do. Same as I would love to have first editions of various books. This is not branding. Branding would thoses forger making thier own original art then advertising it as inspired or done in the style
          • I mean, if you can't tell the difference between the forgers piece and Picasso's then really, whats the difference?

            Maybe the difference is that Picasso came up with the IDEA of the original.

            It's obviously so much easier to copy something that's already there than to create entirely original art.
          • You've got to distinguish between *art appreciation*, and the *art market*. The art market puffs up . Art appreciation shouldn't care about whether it's "really" the original or not. If the two are indisinguishable, then they have the same value. The art market requires authenticity to retain exchange value.

            Many artists and art students aren't that bothered about going to museums to look at work except for research purposes. It's people who are in thrall to the market who go on about the object, or "seein

          • Re:They've got it backwards (Score:4, Insightful)

            by dave420 ( 699308 ) on Wednesday November 24, 2004 @10:43AM (#10908821)
            +5, Missed the entire point of art

            Art is an expression of emotion. Forgers don't express themselves. Your analogy also says that writing is a farce, as anyone can copy out what someone else wrote, ignoring the fact that coming up with the story is the hard part.

            Art isn't about technical perfection, but emotion. Copying art has no emotion, creating art does.

          • Generally the intent of forgeries is not to change the "history" of Art, but simply to make a buck, plain and simple.

            As long as someone is willing to pay a premium for percieved value (above any intrinsic value) there will be those who will try to take advantage of this fact.

        • This will also falsely mark works partially done by students and apprentices as fake. It was a standard practice up to the beginning of the 19th century to have students and apprentices do the "easy" bits and the grand master only finished off stuff. Leonardo did it, Rembrandt did it, so on so fourth.
          • This will also falsely mark works partially done by students and apprentices as fake.

            *Amazing*. Once again a /. geek points a well known fact that the professionals designing the program couldn't possibly know. I mean.. It's only in every art history textbook, on virtually every art history website, in every biography of artists who used this system (not all did). There's just no way the art professionals know this stuff.
        • Ha! I can make a fake Picasso as well as anyone.
          --Pablo Picasso
    • Try this [alias.com] found in one of the papers.

      If you know what to look for you should get a ten out of ten on your first go, and there is no way you'd be able to apply a 'filter' to get realistic results on the CG images.

      I found the nails, screws images hardest, the others were strightforward, look at the depth of field and the detail on the nail/screw head.

      The bonus round's a little harder, mainly becauase they've picked very CG looking images, not realy a good add for 'realism' in maya.
    • I am a painterly rendering researcher,

      What exactly do you mean by "Markov chain an image with that data"? Treating an image as a Markov Random Field means that you assume each pixel is conditioned only on some neighborhood. It's simply an assumption of locality. With that assumption you can do all kinds of things, so it's not clear what approach you're suggesting.

      Also it will be a while before the mall booth has filters accurately reproducing the great artists. To solve the painterly rendering problem
      • > I am a painterly rendering researcher

        Do you have any fun results of your research online? I really enjoyed playing with the work on

        http://mrl.nyu.edu/projects/image-analogies/
        ht tp://mrl.nyu.edu/~perlin/

        and am always on the look out for more interesting things like that.

        Cheers,

        Roger
        • Aaron Hertzmann's work is great, yeah. Aaron's work can be used as an example based system. My work, on the other hand, is model based. I tried really hard to model the painterly process. Not as elegant a solution as Aaron's, but it works better for lots of styles. I don't have any source code to play with. Maybe I will in the next year.

          http://www.cc.gatech.edu/cpl/projects/artstyling /
    • If they have the filter database built for each master, how hard would it be to have it Markov chain an image with that data?

      I'm going to go out on a limb and say, "Damn near impossible."

      The technique described in the paper generates a vector in 72-space(!) that characterizes a given painting. Paintings with similar vectors are associated with a given artist. Attempting to iteratively generate an image which results in a similar vector--while not looking like crap--is probably nearly impossible.

      It's

  • This isn't proof... (Score:3, Interesting)

    by Anonymous Coward on Wednesday November 24, 2004 @02:09AM (#10907117)
    While a statistical analysis of paintings can identify the style of a painter, who is to say that the artist didn't have a change of mood while working on a painting? Or was drinking too much absinthe?

    Painters often change their moods/styles.

    • What? When have you *ever* heard of a moody artist?

    • ah well its even better! they have made a program that can identify the past mood of the painters!
    • well.. maybe they analyze the strokes to see if the artist was drawing a scenery/whatever, instead of copying another piece.

      -
    • While a statistical analysis of paintings can identify the style of a painter, who is to say that the artist didn't have a change of mood while working on a painting? Or was drinking too much absinthe?

      Or how about changes in the artist over time? During his later years, Monet had cataracts in both eyes. You can his later works where the brush strokes are more muddled and the colors were way off. I suppose this program might identify a late Monet vs early Monet but what about those in transition?

  • Stupid idea (Score:2, Interesting)

    by Anonymous Coward
    because unlike fingerprints an artists style and brushstrokes change over time. Go try comparing an early DaVinci with one of this later paintings. If using the early work as a control the later works would be considered fakes, and vice versa if using later works as a control.

    • Re:Stupid idea (Score:3, Informative)

      by Scrameustache ( 459504 )
      Go try comparing an early DaVinci with one of this later paintings.

      Fun stuff you learn in college art history classes: Da Vinci, like a lot of artists, employed a team to do the tedious "painting all day long" parts. He, the master, would of course be an integral part of the process, but most of those are not his brush strokes.
      But they were using the techniques he taught them.
  • Some artists make "modern" art, where no brushes are used, just lopping paint at weird angles. This doesn't seem conducive to this kind of verification.

    • Re:Application it won't work for (Score:4, Funny)

      by Commander Trollco ( 791924 ) on Wednesday November 24, 2004 @02:14AM (#10907143)
      I think you put the quotes in the wrong place.
      Try this: Some artists make modern "art", where no brushes are used, just lopping paint at weird angles. John Cage sucks.
      • > John Cage sucks.

        Yeah, I'd much rather use Raiden or Sub-Zero.
      • Cage sucks only when listened to from a "naive" point of hearing, because he doesn't write music to listen to, but to discuss the state of music in the language of music. For someone being well versed in the musical arts, he does not suck.

        Saying "Cage sucks" is equivalent to my parents saying Jazz/Punk/Metal/Techno sucks, "because it is all the same". It is all the same only for those without experience with these kinds of music, because they haven't learned to hear what it is about. To me, most 17th/18rh
        • Indeed, it isn't all the same at all. I loved the diversity of sound in 4'33". I mean, opening the piano lid, and closing it! What brilliance! I wish I could come up with something like that.
          • Cage 101: The music in 4'33" is the sound that the audience makes. Interesting if you ask me, but maybe only for regular concert goers.
            Interesting also that 4'33" is always the only thing people who argue against Cage come up with. Maybe try to listen to other works and try to see it in context?

            And I'd appreciate a link to the art you created. You seem to be quite good. Thanks
    • Nor is it conducive to easy forgery either. It would take a lot of work to put all the splashes and drips in the right places, and even minor mistakes would be easily noticed if compared to a photograph of the original. For the forger to just lop the paint on himself of course will never get it to look identical.
  • They said it's an authentic Pollock!

    Damn racists!
  • i'll have to read more on the method, but i'm skeptical of most art classification systems. I'm also curious what exactly it is that they're learning from the peices of artwork they're generalizing over (yes yes, i'll have to RTFP), hopefully they're not doing what was done with early artificial neural networks that is, simply letting the algorithm decide what unconstrained features it found common across all the paintings.

    or in other words, sounds like it's not too shabby with recall. so what's its prec

  • Wow Dude!!! (Score:4, Funny)

    by dnaboy ( 569188 ) on Wednesday November 24, 2004 @02:15AM (#10907150)
    They used weed to fake out art?

    Damn, I knew those CS kids in College must have been up to SOMETHING productive...

  • hmmm (Score:2, Funny)

    by Neil Blender ( 555885 )
    CSI? Fake life imitating science detecting imitation art?

  • Except... (Score:3, Informative)

    by gonerill ( 139660 ) on Wednesday November 24, 2004 @02:17AM (#10907157) Homepage
    ... promises to reduce the subjectivity of art assessments made by human experts. Except with respect to bootstrapping the authentication process in the first place.
  • How many times have you heard "a 6 year old could have painted that". Why not take a leaf from the "million monkeys" and get a million 6 year olds with a million paint brushes, bucket loads of paint in the primary colours and bamn! All the great works reproduced with no chance of digital fake detection.
    • > How many times have you heard "a 6 year old could have painted that"

      Whenever I hear that I say to the person, fine, so please go find a 6 year old to paint that! Just because it "looks" easy does not mean it is easy. Also remember that sometimes the act is not as hard as getting the idea.

      Ok, once I was caught because there was a 6 year old how could paint. My friends son was a good artist.

  • Mona Lisa (Score:4, Funny)

    by Ridcully ( 121813 ) on Wednesday November 24, 2004 @02:17AM (#10907159)
    But can they detect the message "This is a fake" written with a modern felt tip pen under the painting of the Mona Lisa?

  • It works (Score:4, Funny)

    by Tablizer ( 95088 ) on Wednesday November 24, 2004 @02:18AM (#10907166) Journal
    It told me that 80% of my porn is fake. They are all westerner heads pasted on Indian bodies. Not that I mind Indian babes, but resent being tricked. I refuse to outsource my pleasure based on wage alone.

  • Producing fakes (Score:4, Insightful)

    by femto ( 459605 ) on Wednesday November 24, 2004 @02:26AM (#10907199) Homepage
    What's to stop a smart person flipping the algorithm 'upside down' and using it to create works of art which can be passed off as being by a master?

    For example, analyse a collection of paintings by a particular master. Next paint a picture yourself. Finally, introduce random 'mutations' to your painting, running each mutated painting through the fake detector and selecting the best mutation as input ot the next iteration. The result might just be your very own 'Raphael'.

    Such a painting would be undectable by the computerised fake detector, since the painting was 'defined' to pass the detection process. If the computer is better at analysing paitings than humans, presumably your new masterpiece would also past any inspection by a human.

    • Until someone noticed that it was printed out by a color printer.

      Oh and look there is your serial number encoded in nearly invisible yellow pixels.
      • Until someone noticed that it was printed out by a color printer.

        Then get hold of a plotter, load it up with pantbrushes and use that.

        • I hope this is a joke, because plotters are laughably inadequate to the task of producing the range of brush marks found in master oil paintings. Remember, painters vary:
          * degree of paint mixing
          * brush load
          * brush angle (varying even within a single stroke) both relative to canvas and relative to stroke direction.
          * brush rotation (along the axis of the handle, also varying even within a single stroke)
          * brush pressure (varying even within a single stroke)
          * brush direction (of course varying within a single s
    • You'd need to write drivers for /dev/paintbrush!
  • Equilibrium? [imdb.com]
    (Kick ass movie, must see!)

  • Interesting definition of value (Score:3, Insightful)

    by chthonicdaemon ( 670385 ) on Wednesday November 24, 2004 @02:29AM (#10907216) Homepage Journal
    Art fraud is one of the places where the definition of value becomes very interesting. It makes it very clear that the value in a painting lies in more than its utility as a picture (even a very beautiful or skillfully made one).
  • I have always wondered about this from a handwriting perspective. I have a strange writing style which is very dissimiliar line by line. some slants back from the top, some goes forward, some cursive, some print, some all-upper, etc. I write some characters starting at the top, some at the bottom, sometimes not the same word to word. I am sure art is even worse based on the artist's mood, experience, medium, etc. Anyone here had their handwriting analyzed?

    • I have a strange writing style which is very dissimiliar line by line. some slants back from the top, some goes forward, some cursive, some print, some all-upper, etc. I write some characters starting at the top, some at the bottom, sometimes not the same word to word.

      This just means you suck at writing.

      Haha, kidding, I do most of that sutff too.

  • Jackson Pollock (Score:5, Interesting)

    by Bowling Moses ( 591924 ) on Wednesday November 24, 2004 @02:39AM (#10907256) Journal
    This reminds me strongly of a talk I went to by Richard Taylor, a physics prof at the University of Oregon. He's determined that Jackson Pollock's paintings are fractal [uoregon.edu]in nature, and is one of the people contacted when a new painting of his turns up. So far, he's been in total agreement with expert opinion. An interesting note is that Pollock got to a "sweet spot" of what Taylor calls "drip fractal dimension" of ~1.6-1.7, whereas nature is around about 1.2-1.3. Pollock, Taylor said, seemed to want to challenge the viewer with more intense fractal patterns. He could get higher drip fractal dimensions, to a value of greater than 2, but he decided it was too far and painted over it--too challenging or something. This was something mentioned in Taylor's talk, not in the link. Anyway, it was a really interesting talk that's made me look for repeating patterns in nature when I'm out hunting or something, and gave me a greater appreciation for Pollock's paintings, which always used to look like...er...Jackson Pollocks to me. Also Taylor talked about how fractal nature seems to be appealing and relaxing to us, with our mood improved if there are either real plants or large photographs of natural scenes around our cube farms--which are incredibly unfractal like and horridly plain and repetitive.
    • IIRC, Pollock used cheap house paint which only lasts 10-20 years outdoors, so his paintings are all deteriorating.

      I've seen a couple of his works, and they looked quite dried out to me.

      I would think it would be terribly difficult to forge one of his paintings today, unless there is some way to age the paint rapidly.
  • those chairs in the picture are really expensive....

    (my previous job used them everywhere)

    and are very comfortable - especially for long periods of time

    game on!

  • Fingerprinting a Artist isn't validating ART (Score:3, Interesting)

    by infonography ( 566403 ) on Wednesday November 24, 2004 @02:49AM (#10907297) Homepage
    It's plausable to find simalarities in a painting from one to another. You can get a fair match most of the time. But you would need a large sample over the life of an artist. How will illness, age, drunkenness, absenth and other drugs effect the painting style of a artist? Really I can't place too much faith in the tech here. The old standard of Carbon Dating would be more effective. Sorry try again.

    • It's plausable to find simalarities in a painting from one to another. You can get a fair match most of the time. But you would need a large sample over the life of an artist. How will illness, age, drunkenness, absenth and other drugs effect the painting style of a artist? Really I can't place too much faith in the tech here.

      And why precisely can't a computer assign a value to the 'closeness' of a given painting to a given period of a given artist? It's a rare artist that is considered important enough

    • >How will illness, age, drunkenness, absenth and other drugs effect the painting style of a artist?

      This software will is actually being modified to meassure the alcohol level of the artist at the time of the painting. The new version will also include drug testing, so the next time you are asked to do an oil painting at a job interview (you know, this actually happens all the time), you should really consider if it's worth it ;-)

      /Spiff

  • Human Artists Are Not Droids (Score:3, Interesting)

    by Maljin Jolt ( 746064 ) on Wednesday November 24, 2004 @04:08AM (#10907488) Journal
    I had a friend, a painter and sculptor. (If he is still alive, he would be 102 this year.) During his artistic career over 7 dekades he changed his techniques dramatically several times. Some artists are permanently seeking something new instead of mining money on salon style du jour.
  • Of course, if an artist sticks to the same techniques during his lifetime, he'll be identified. If a "known limitation" of the method is that it can only compare paintings of the same type, then you still risk the possibility that say Rembrandt decided to paint a picture with his left hand instead of his right because he hit his right thumb with a hammer while fixing his house. This will falsely label a picture as a fake.

    Similarly, in the time of Rembrandt, it was common to have helpers paint the less impo

  • Slashart (Score:4, Insightful)

    by The Dodger ( 10689 ) on Wednesday November 24, 2004 @04:42AM (#10907578) Homepage
    The method ... promises to reduce the subjectivity of art assessments made by human experts.
    Pointless from a purely art standpoint, albeit potentially highly amusing from the financial standpoint.

    Art is subjective. This software might be able to fingerprint an artist's style, but it's up to me/you/us to decide whether a painting is "good".

    I can go out, buy a canvas and some paints, come back home and paint something abstract. If it's interesting or pleasing to the eye, I might be able to sell it to a small gallery or at an art fair and even make a profit over the cost of my materials. However, if someone like Damien Hirst does the same thing, it's going to sell for tens of thousands of pounds, purely because of the artist's name.

    So, what if this software reveals that the Sunflowers weren't actually painted by Van Gogh? One thing's for sure - the painting would be worth a lot less, even though it's the same painting. The valuations are all artificial.

    In general, I kinda like a lot of Monet's paintings. I'll buy a print of one of his "Houses of Parliament" paintings, or "San Giorgio Maggiore at dusk". If the opportunity arose, I wouldn't mind owning one of the originals and I'd even be prepared to shell out quite a few readies for it, because he's a popular artist, lots of people like his paintings and, therefore, other people are going to want to own it as well. So, for argument's sake, let's say I'm prepared to pay up to the equivalent of, say, 4% of my annual salary (before tax), for one of those paintings. That's never going to happen, because original Monets are valued in the millions.

    But, the thing is, if it turned out that Monet hadn't painted that painting after all, I'd still be prepared to pay the same amount of money, because it doesn't really matter to me whether it was painted by Monet or by some unknown artist - I still like the painting and that's what it's worth to me as a piece of art.


    D.

    • Re:Slashart (Score:4, Insightful)

      by a24061 ( 703202 ) * on Wednesday November 24, 2004 @05:07AM (#10907624)
      But, the thing is, if it turned out that Monet hadn't painted that painting after all, I'd still be prepared to pay the same amount of money, because it doesn't really matter to me whether it was painted by Monet or by some unknown artist - I still like the painting and that's what it's worth to me as a piece of art.

      That could well be true at the lower end of the price range for art, but I doubt it would apply at the high end (e.g. Monet)---where art prices are based mainly on speculation. If you bought a fake Monet for the price of a real Monet, you would never be able to get a similar price for it if you sold it later (for example, if you needed the money or your tastes changed).

      • Mmm.. I didn't make my point very clearly. Hadn't had any coffee at the time.

        You're absolutely right, but I wasn't implying that the "real" value (i.e. in the millions) would be unaffected by the painting being exposed as a fake - I was saying that it's value to me (i.e. the few thousand I'd be prepared to pay for it, rather than the millions it would get in reality) would be unaffected, because it's still a nice painting, no matter who painted it.

        My point is that art is subjective and in my opinion (wh

  • Waste of time (Score:3, Insightful)

    by glMatrixMode ( 631669 ) on Wednesday November 24, 2004 @04:56AM (#10907602)
    It's time one realizes that art authentication is totally useless : if a copy is so good that humans fail to see any difference from the original and need machines to do so, then the copy isn't less good than the original. That's all.

    If, regarding to this matter, there's anything computers can help with, it's understanding that allowing copies without restriction is not necessary as "evil" as some pretend to think.

    This would have been considered obvious a few centuries ago. Art has not always been about the author.

  • Automated image analysis a common tool these days (Score:3, Informative)

    by HuguesT ( 84078 ) on Wednesday November 24, 2004 @04:58AM (#10907605)
    This is good work, but what is so special about it?

    Using image analysis, "computers" these days do:

    - Automatisation of drug discovery screening tests [axon.com]
    - Diagnosis of skin cancer [csiro.au]
    - Detection of early breast cancers [ge.com]
    - All sorts of QA in assembly lines [manufacturingcenter.com]
    - And much much more, these are just examples you can find googling a bit.

    Why is this news? If you go to any computer vision [microsoft.com], image analysis [iapr.org] or pattern recognition [hkbu.edu.hk] conference, you'll find many similar applications.
  • Just do an MD5 sum on a Monet, or check if it has been signed by him, has anyone checked what his public key is?

    How inconsiderate of them. I can usually tell a fake, it is slightly forced, has a few false starts, and is often more vocal than a real one, less perspiration and moisture overall, and certain muscle contraction signatures differ. :-)

    For those of you who are thinking about oil paint composition and machine analysis of muscle movements of a painter, then congrats, you belong to /.!

  • Just another example of what's wrong with IP (Score:3, Insightful)

    by panurge ( 573432 ) on Wednesday November 24, 2004 @07:18AM (#10907914)
    As other posters have pointed out, this is not about the value of art. It's about the value assigned to something by linking it with a famous name. The joke is that we don't even have Leonardo or Botticelli around to cash in on their fame: the "value" of something being by Leonardo da Vinci is purely notional. If a program can identify that a painting over which experts disagree is "really" a Giovanni Ferrari rather than "really" a Leonardo, the value decreases enormously despite the fact that someone thought the painting was good enough to be a Leonardo in the first place. It isn't even about originality: at this remove we do not know whether Leonardo was original or whether he copied the ideas of someone else whose work is now lost.

    So, since this is purely a commercial program whose purpose is to provide a notional valuation based on association with celebrity, expect it to be extensively challenged. Too much is at stake. The art experts will soon weigh in there: the brush strokes being evaluated are actually those of the atelier assistants who did most of the work, the bits actually by the master defy analysis by a machine, and so on. Part of the value of the art market depends on gambling: finding the missed masterpiece, having a painting lose value owing to wrong attribution only to have the perceived value of the "real" artist increase as fashion changes. Anything that introduces apparent certainty will partly destroy the churning process that pushes art prices upwards, and no-one in the market wants that.

    The price of art is as unrelated to the long-term assignment of aesthetic values as the price of CDs is unrelated to the actual merits of the performers. That's the sad reflection on our society.

  • At our department we have been doing this for years [unimaas.nl].

    It is actually not that difficult, but many people are enormously impressed by the results.

  • Just like when your bank flags your transactions for Homeland Security secret investigations, when you make a "historically unusual" transaction like buying a motorcycle for cash, art detectives will be denying authenticity of artists' most experimental works. Great artists change with every brushstroke - their career is a dynamic learning process, interacting with their medium as much as with their audience. As years go by, only their most predictable work will get credit. At least their fringe art will co
  • Damn, I miss that era when "Computers used to do X" was always newsworthy no matter how mundane the X was ("Computers used to typeset newspapers"). The whole article looks like something written 20 years ago or so and sadly it is replicating some fake asumptions that since them were sufficiently refuted. The method (...) promises to reduce the subjectivity of art assessments made by human experts." If it does, don't believe this promise. You don't get magical infallibility just becouse you use a computer. E
  • I misread the subject as "Using Computers To Weed Out Fake Farts". It could be a useful technology.
  • Picasso was once given a bet that he could not tell his own paintings from his very astute forgers. He took the bet, was offered a lineup and proceded to pull out all the forgeries and additionally three of his own paintings. When this was pointed out to him, he replied, "I can fake a picasso as well as anyone."
  • It's funny how people care more about who painted something than the actual content and form of the painting.
  • Elmyr de Hory [crimelibrary.com] was one of the greatest forgers of all time, and a really interesting guy.

    Clifford Irving, who was also a forger in his own field, wrote a really good book on de Hory, titled Fake! (with the exclamation).

    And then of course Orson Welles made a film [wellesnet.com] exploring these issues.

    All highly recommended. The art forgery world is at least as interesting [mystudios.com] as the "legitimate" art world. [artnet.com]

    If you want to get into it, there's a primer [amazon.com] available.

Slashdot Top Deals

There are two ways to write error-free programs; only the third one works.

Close