Slashdot Mirror

← Back to Stories (view on slashdot.org)

Using Computers To Weed Out Art Fakes

Posted by timothy on 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."

15 of 192 comments (clear)

  1. They've got it backwards by Dancin_Santa · · Score: 5, Interesting

    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.

    1. Re:They've got it backwards by SerpentMage · · Score: 4, Interesting

      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!

      --

      "You can't make a race horse of a pig"
      "No," said Samuel, "but you can make very fast pig"
    2. Re:They've got it backwards by HyperCash · · Score: 4, Interesting

      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

      --
      So I'm jump'n up and down screaming show me the money.
    3. Re:They've got it backwards by arivanov · · Score: 2, Interesting

      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.

      --
      Baker's Law: Misery no longer loves company. Nowadays it insists on it
      http://www.sigsegv.cx/
    4. Re:They've got it backwards by will_die · · Score: 2, Interesting

      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 of someother artist in order to sell it for a higher price then thier work alone could do.

      Now if you want to see what makes a real mockery look at modern art and vaccum machines in plastic boxes.

    5. Re:They've got it backwards by Anonymous Coward · · Score: 1, Interesting

      How then should we regard, as another poster has mentioned, forgers/artists who produce original art under a famous artist's name?

      Fact is, if you go to the museum and look at all these paintings by the old masters, they are not all painted by one person. Back then, the old masters had assistants, and they themselves were assistants to some other artists before they made a name for themselves. Sometimes the assistants took part in the underpainting, but sometimes they actually put in work that is as visible as any other part of the painting in the final work (painting, say, minor figures surrounding the dominant ones). Clearly, these assistants has to paint in a style that is very similar to their master, otherwise the painting will fall apart.

      Are these assistants forgers?

      Ah! you say, they had permission by the the person whose name to which the painting is attributed. True. But does it matter? A painting is a painting is a painting. One must not let all these ethical issues take on the main role, and dominate all other issues.

      Theoretically, is it not possible that an artist can produce an ORINGIAL piece of work in a style that is indistinguishable from an old master's, and then attribute authorship to that old master?

      The "forger" may even put a lot of his own emotion into the forgery. Why does he do it? Maybe he just wants to feed himself, and he isnt so vain as to want people to acredit a good painting to his name. Art is art is art, big name or small name, old master or art student. Perhaps the forger/artist just wants to create art and live comfortably--Who can blame him?

      On the other hand, if they find out that his painting is not by an old master, the price will probably drop by hundreds of thousands of dollars. REGARDLESS of its artistic merit.

      So a painting has all these aspects, to name a few: art, art history, ethics.
      Are you telling me that the last two is worth most of the price of the painting?

      If some art buyer bases his budget of whether a painting is really done by certain old master, then he/she ceases to be an art buyer; he/she is nothing but an antique collector, and a vain one at that.

      p.s. You may have guessed that I have a certain degree of distain towards a certain class of purchasers of paintings. I do concede that I do not have an argument for the intrinsic superiority
      of an art buy over an antique collector. Hence, the whole discourse can easily fall apart. Oh well.

  2. This isn't proof... by Anonymous Coward · · Score: 3, Interesting

    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.

  3. Stupid idea by Anonymous Coward · · Score: 2, Interesting

    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.

  4. I'm Skeptical still... by NoTheory · · Score: 2, Interesting

    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 precision?

    --
    There are lives at stake here!
  5. Re:I found an old dropcloth in my shed by starm_ · · Score: 2, Interesting

    I think they could even guess what year a painting was painted just with the fractal depth. It turns out the fractal depth of his paintings gradually increased over the years.

  6. Jackson Pollock by Bowling+Moses · · Score: 4, Interesting

    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 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.

  7. Fingerprinting a Artist isn't validating ART by infonography · · Score: 2, Interesting

    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.

    --
    Sorry about the writing. Robot fingers, you know? Cliff Steele in DOOM PATROL #23
  8. Re:I found an old dropcloth in my shed by starm_ · · Score: 2, Interesting

    Obviously that's how they could determine that their model had good prediction. If they didn't have the dates they could not have tested their theory.

  9. Human Artists Are Not Droids by Maljin+Jolt · · Score: 2, Interesting

    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.

    --
    There you are, staring at me again.
  10. CG aint that good. by oliverthered · · Score: 2, Interesting

    Try this 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.

    --
    thank God the internet isn't a human right.