Forgot your password?
typodupeerror
AI Technology

Machine Vision Reveals Previously Unknown Influences Between Great Artists 74

Posted by samzenpus
from the spilled-like-pollock dept.
KentuckyFC writes Art experts look for influences between great masters by studying the artist's use of space, texture, form, shape, colour and so on. They may also consider the subject matter, brushstrokes, meaning, historical context and myriad other factors. So it's easy to imagine that today's primitive machine vision techniques have little to add. Not so. Using a new technique for classifying objects in images, a team of computer scientists and art experts have compared more than 1700 paintings from over 60 artists dating from the early 15th century to the late 20 the century. They've developed an algorithm that has used these classifications to find many well known influences between artists, such as the well known influence of Pablo Picasso and George Braque on the Austrian symbolist painter Gustav Klimt, the influence of the French romantic Delacroix on the French impressionist Bazille, the Norwegian painter Munch's influence on the German painter Beckmann and Degas' influence on Caillebotte. But the algorithm also discovered connections that art historians have never noticed (judge the comparisons for yourself). In particular, the algorithm points out that Norman Rockwell's Shuffleton's Barber Shop painted in 1950 is remarkably similar to Frederic Bazille's Studio 9 Rue de la Condamine painted 80 years before.
This discussion has been archived. No new comments can be posted.

Machine Vision Reveals Previously Unknown Influences Between Great Artists

Comments Filter:
  • Copyright harassment (Score:5, Interesting)

    by tepples (727027) <tepples@gmaiBLUEl.com minus berry> on Monday August 18, 2014 @11:16AM (#47695357) Homepage Journal
    How long until dead artists' heirs latch onto techniques like this to prove "substantial similarity" as part of a copyright suit to try to squeeze money out of working artists?
    • by Bogtha (906264)

      Isn't there a short story about a songwriter who kills himself after losing a court case for plagiarism because there aren't any original melodies left?

    • How long until dead artists' heirs latch onto techniques like this to prove "substantial similarity" as part of a copyright suit to try to squeeze money out of working artists?

      It's been going on in music since recording started.

      If you're not an artist, if you're not a musician, it's easy to listen to something like this:
      https://www.youtube.com/watch?... [youtube.com]

      and assume plagiarism.

      The fact of the matter is, in music, There really is nothing new under the sun. You can't write a "new song" period. Every chord you use, has been used before. Every rhythm, every melody. In that case, Satriani knows what he's doing is BS... that guys always been a jerk. But the reality is. all music produced

      • by tepples (727027)
        I understand that. I have in the past made a combinatorial argument that only 105 million distinct 8-note melodic hooks exist, and I currently maintain a list of similar-sounding musical compositions [pineight.com]. I just wonder what steps a visual artist, songwriter, or any other author should take to reduce his legal exposure.
      • Thank you for that link. Great band.
        I am a huge fan of bands like Nightwish, Epica, Within Temptation and the like.
        I now have a new one.

        Thanks.
  • I suppose the only way people will quit caring more about which artist drew something than how it looks, is if we replace artists with computers.

    • Personally, I'd kill to get a picture frame running LAKESIDE.BAS. Sadly, I've lost my copy of this late 80s "BASIC 2" curio, and since it was pre-Internet, it seems lost in time.

    • by Anonymous Coward

      http://en.wikipedia.org/wiki/Algorithmic_composition

      People are already working on it. Some of it is pretty good.

    • the whole "man vs machine" conversation has gotten hopelessly muddled by "AI" hype from Kurzweil types & pop science news...

      is if we replace artists with computers.

      impossible...computers are complex machines that follow instructions

      what you mean is, "if we continue programming computers to generate art"

      the "artist" is whatever monkey programs the machine to make the art....UNDERSTAND THIS FOREVER AND INTEGRATE IT INTO YOU PERSONAL PHILOSOPHY

      the researchers in TFA are doing some interesting work, but the

      • is if we replace artists with computers.

        impossible...computers are complex machines that follow instructions

        So are artists.

        • humans are not "just machines" because we can **choose to program ourselves and formulate/test hypothesis that we communicate/share/compare with others**

          humans **can be** programmed...yes...

          ways you can "program" a human:

          > control information they receive
          > physical/emotional abuse
          > chemicals (alchohol, 'roofies', etc)
          > the Frey Effect [wikipedia.org]
          > cattle prod

          note: all of the above are **abuse** and illegal without informed consent

          so you're wrong...humans cannont "be programmed"....the can surely "be abus

          • humans are not "just machines" because we can **choose to program ourselves and formulate/test hypothesis that we communicate/share/compare with others**

            So can computers. Computers can run arbitrary code. Computers can generate arbitrary code. Humans are much more limited in their ability to chose how their mind functions (which is ironically why many people think humans have free will).

            • Running arbitrary code doesn't meany anything more than a jump table. Humans are far more capable of altering their thinking patterns, studying and adopting new pattern on their own and even forgetting things, making for new overall outlooks. Short response: you are so completely wrong.
              • Well, consider if a computer decided to quit smoking. Its thought process would go something like this:

                Smoking.Exit()
                WantToSmoke = false;
                Nicotine.AddictionTo =0;

                A human's thought process would go something like this:

                while (true)
                {
                if (random.Next() % Nicotine.AddictionTo == 0)
                {
                throw new Event("I want a cigarette");
                Shame = Shame + 1;
                if (UrgeToSmoke > Willpower)
                {
                Smoking.Add(

                • A human's thought process would go something like this:

                  yeah...I see now...

                  so I run VooDooCode...it looks like this:

                  1 eye of newt
                  1 heart of chicken (fresh)
                  4 feet of black cat born under full moon
                  1 gallon pig blood

                  the position of the elements of the code determines the future of the person who I am reading

                  like your idea, VooDooCode explains human behavior simply, and proves that humans are "just machines"

                  • No, no, no.
                    You've got to use Goats!

                    http://www.bing.com/search?q=voodoo%20sacrifice%20with%20goats%20and%20chickens&pc=cosp&ptag=A75DB878ECBE148E7B6F&form=CONBNT&conlogo=CT3210127

                    (just a link to a search of voodoo spells involving goats. NOT a goat.cx link! I value your eyes, but not your sanity, therefor, a Bing link.....muhahahahaha)
  • by kruach aum (1934852) on Monday August 18, 2014 @11:27AM (#47695467)

    What the computer can do is point out what is similar. Whether the similarity is an example of influence then needs to be established with further evidence.

    • by Chrisq (894406) on Monday August 18, 2014 @11:32AM (#47695533)

      What the computer can do is point out what is similar. Whether the similarity is an example of influence then needs to be established with further evidence.

      Of course even if there is influence it may not be direct. Both artists could have been influenced by another earlier artist, or the second one influenced by an intermediate one, or there could be a whole complex tree of influences

    • The human needed to establish that influence can establish that similarity as well, rendering the computer superfluous.
      • Establishing the similarity is something computers excel at, though. Just because I can work out by hand what 4565 * 2349 equals doesn't mean a computer can't do it much faster and with a lot less hassle.

        • You can't use mathematical computation an example that's anywhere near similar to this as similarity in art is far more than if both items contain a rectangle. The worthiness of this particular algorithm depends on the percentage of false positives. Only going by the items in the article, I count three for three false positives. A waste of human time to review.
      • by plover (150551) on Monday August 18, 2014 @12:27PM (#47696011) Homepage Journal

        The human can only do that if both pictures come to his attention. But there is so much out there that it's almost impossible for someone to be familiar with every piece to the extent they'd be able to recognize them. The computer has infinite patience, it can attend to vast quantities of the most minute details, it has a catalog that doesn't fade with time, and the ability to re-run increasingly sophisticated algorithms as new ideas are brought to bear.

        For example, Rockwell's barber shop and Bazille's studio share a few subjects in a few common locations, but it's hard to look at them and say "there was an artistic influence." Rockwell was noted for realistic depictions of idyllic Americana, so any influence there would likely have been the architecture of the setting and the choices of overall composition and balance. Choosing to include a group of three people, an unoccupied chair, and a wood stove, does not seem to imply much more than coincidence. But if you weren't comparing every item in the catalog with every other item in the catalog, you might not have bothered to notice at all.

        Which brings us to the real question: how would knowing the answer (or even asking the question) make a difference to the world?

        • by g01d4 (888748)
          I would agree w/some of the other posts that the algorithm seems a bit primitive. Perhaps on refinement it may point out correlations that may either be influence or perhaps represent certain stylistic archetypes hitherto unknown. I think asking and knowing make a "difference" but the question is somewhat subjective.
          • by plover (150551)

            Actually, the more I look at the Rockwell and the Bazille, the more sophisticated the results of the comparison appear to be. You've got a group of men, off in the background, engaging in a conversation that you are not able to hear. They're the subjects of the piece, but you don't see much of them, you can't hear what they're saying, and what they're talking about is partially obscured. You assume that because they're invited to the back room of the barbershop that they're more than just customers, simi

            • I still think that the paintings are likely unrelated to each other, but it seems that both artists were thinking similar thoughts when they chose to paint these. And that's the sophistication of the algorithm.

              Unfortunately, it's not the point of the algorithm, so that sophistication is projected upon it by you, not intrinsic to it's conception. You yourself invalidate the point of the algorithm with the beginning of your sentence. There were no influences between the artists, only similarities. Which i

    • Art is taught and can be learned, I study this as well as everything else I can find to learn (yes, even at a University). What an artist learns is how to move a persons eye, and how to make aesthetically pleasing art, amongst other things.

      As an example, If you draw an X in the center of the canvas and maintain the lines in the painting, people's eyes will be drawn to the center. Numerous Xs will have numerous focal points. Great artists know this, and obscure the lines so it's harder for people to notic

  • by Joe Gillian (3683399) on Monday August 18, 2014 @11:30AM (#47695507)

    I looked at the Rockwell/Bazille comparison, and they don't really seem all that similar - they have three similar elements (stove, chair, and window) but those seem coincidental more than anything. The window in Rockwell's piece, for instance, is small and rectangular while the one in Bazille's is huge and arched. The chair in the Rockwell piece is actually barely identifiable as a chair at first glance, whereas the one in the Bazille piece is immediately recognizable as a wooden chair. They're also three objects that are likely to be close to one another. For instance, my aunt heats with wood and has a stove roughly the same distance from a window as in the Rockwell and Bazille pictures, and if I remember right even has a wooden chair in the same room. I think all this proves is that people tend to put their stoves in rooms with windows and chairs.

    • by oodaloop (1229816) on Monday August 18, 2014 @11:36AM (#47695591)
      I suppose that's why they say this then:

      ...Saleh and co do not claim that this kind of algorithm can take the place of an art historian. After all, the discovery of a link between paintings in this way is just the starting point for further research about an artist’s life and work.

      • That is nowhere near a strong enough caveat to overcome their claim the algorithm finds artistic similarities. That kind of algorithm cannot take the place of common sense.
    • by vux984 (928602)

      they have three similar elements (stove, chair, and window)

      First you oversimplified the similarities, and you then minimized its significance. Minimizing AFTER oversimplifying is essentially a straw man argument.

      The window in Rockwell's piece, for instance, is small and rectangular while the one in Bazille's is huge and arched.

      They are both structurally rectangular and similarly proportioned (height vs width).

      The chair in the Rockwell piece is actually barely identifiable as a chair at first glance, wher

    • by Spamalope (91802)
      Exactly. If you analyze enough art done by artists who understood composition and the rhythms color, form, space and lighting should take for a pleasing effect you'll see those things repeated. It's not too surprising that two 100 year old inside scenes would both include a doorway, chair, stairs, stove - any common interior furnishings - or that they'd be arranged for the best compositional effect.

      Show me how Bazille's paintings recognizably show their his work, then demonstrate Rockwell including those
  • I don't see it (Score:4, Insightful)

    by Nidi62 (1525137) on Monday August 18, 2014 @11:32AM (#47695531)

    So...because Rockwell and Bazille's paintings both have windows, people, a chair, and a stove they are influenced by each other? All of these are common things that you would expect in any building in the late 1800s and mid-50s (note the age of the building implies it is not new construction at that time and would definitely still rely on a stove for heating). I guess they are trying to argue that the placement of the items is the connection? Barbershops always have their chairs on one side near the wall, and people tend to put chairs near walls and objects as well, not in the middle of the floor. The right angle formed by the wall and floor and then the pane in the window seems a bit of a stretch, since wouldn't any painting of a man-made structure include right angles at some point?

    I guess I just don't "get it"

    • by c (8461)

      I guess they are trying to argue that the placement of the items is the connection?

      Pretty much. I suspect this is one of those situations where "correlation != causality" is an appropriate comment.

      • Re:I don't see it (Score:5, Insightful)

        by Skewray (896393) on Monday August 18, 2014 @12:22PM (#47695977) Homepage

        I guess they are trying to argue that the placement of the items is the connection?

        Pretty much. I suspect this is one of those situations where "correlation != causality" is an appropriate comment.

        I would say instead that, given a sufficiently large enough data set, patterns and correlations are bound to appear. The likelihood that thousands of paintings were analyzed in this way and no matches were found, purely on a random basis, is very small.

    • by NekSnappa (803141)
      It's more than just that the two paintings share 3 or 4 similar items. There's also where they lie within the composition.

      Then there's the overall composition of the piece. The overall balance is similar although one biased to the right the other to the left, and the similar trait of something slanting into view at the left edge at about the same angle.

      The subject matter doesn't even have to be the same in order to draw similarities. They just used those examples because they illustrate the point of the a

    • by jedidiah (1196)

      Just like with evolution, two similar things don't have to be parent and child. They can be siblings or cousins sharing a common origin.

      Rockwell and Bazille likely share common influences including the general culture at large.

      This is the sort of thing that should be obvious to anyone that's ever been in any serious kind of art museum. Art documents the culture that created it. You can easily see how that changes over time.

      A number of these cultural transitions are really quite dramatic.

  • M.C. Escher (Score:5, Funny)

    by The Grim Reefer (1162755) on Monday August 18, 2014 @11:34AM (#47695559)
    Interestingly when M.C. Escher paintings were analyzed it kept returning "divide by zero errors". Upon further examination, it was discovered that it was claiming "divide by the letter "O" errors" and not the number zero.
    • I started thinking about Escher too when I read this, and maybe it's because my knowledge of art history is simply inadequate, but I couldn't think of any artist influenced by Escher other than the creator of the Berserk manga, Kentaro Miura. And even there "influence" may be too strong, as it's more that Miura visually references Escher a couple of times.

      • by Anonymous Coward

        but I couldn't think of any artist influenced by Escher other than the creator of the Berserk manga

        but I couldn't think of any artist influenced by Escher other than Escher being any artist influenced by Escher other than Escher.

    • by steelfood (895457)

      Once, the program somehow found itself in an infinite loop and had to be killed with -9. This despite it having been proved terminating.

  • Do you think Chris Hadfield was influenced by David Bowie?

  • Just using the bottom example. The 'related' elements are that each painting used a window, each painting had a small group of people (the first in mid-ground, the second in a back room), each had a pipe shaped heating stove, each had a piece (different) of furniture and each had a diagonal element (both differing angles).

    Those things, they think, may be from influence instead of, say, the fact that humans have all those things in everyday life.

    Their algorithm and their view of its output needs a lot of

    • by imatter (2749965)

      ...and did they check the results against living artist that can tell you their influences?

      I imagine that Pollock drip paintings would not show the influence of Picasso.

      • If they need to check with living artists for validation, the entire exercise is worthless as the bulk of the artists are dead.
    • by plover (150551)

      It's not just the furniture and the occupants, but how the artist chooses the scene. There is a balance to a picture, with different ways to give the painting a sense of place, or to guide the eye to focus on that which is more important to the artist. The artist could choose to leave out the stove. He could choose a time when the room has more or fewer people, or when the faces are distinct or obscured, whether or not they're facing the artist, etc. Rockwell chose to paint a barbershop with no customer

      • Everything you say may indeed be true, but the point of the program is to find influences between artists, not similarities in their works.
  • This can only lead to the Facebookization of the art world. No thank you.
  • http://en.memory-alpha.org/wiki/Requiem_for_Methuselah_%28episode%29 [memory-alpha.org]

    The machines have found proof that we have an immortal painter living who's been changing names throughout history!

  • >> In particular, the algorithm points out that Norman Rockwell's Shuffleton's Barber Shop painted in 1950 is remarkably similar to Frederic Bazille's Studio 9 Rue de la Condamine painted 80 years before.

    Not at all. Apart from both being of (different sized) rooms painted from an approximately similar angle, there really is nothing else that is the same about the two paintings. It would appear that the computer is keying only off of very large features such as a general observation that a large lights

  • An algorithm scanned through images of works of art, and identified similarities. And that means what?
  • It is well documented that the african art in beginning of 1900's started to be taken seriously through expositions. Picasso never made a secret of this influence.
    Makonde wood carvings such as the ones with shetani on long legs, influenced Dali to paint those elephants on long legs.
    On a funny note you should check out Martin Schwarz (for reference: Giger liked him a lot) work: he painted the mona lisa without the mona lisa - he found the background to be more inspiring.
    Art is never a coincidence - this i
  • From the article:
    "They've developed an algorithm that has used these classifications to find many well known influences between artists, such as the well known influence of Pablo Picasso and George Braque on the Austrian symbolist painter Gustav Klimt, ..."

    I never heard that before. In what way did Picasso and Braque influence Klimt's art?

    • I think it is unlikely that Klimt was influenced by Picasso. Picasso was 19 years younger than Klimt and by the time he became famous Klimt's had already established his style. The situation appears to be similar with Braque. I think the article's claim that "indeed experts are well acquainted with the idea that Klimt was influenced by both these artists" could be a mistake.

"Pull the trigger and you're garbage." -- Lady Blue

Working...