The Machine Vision Algorithm Beating Art Historians at Their Own Game

Classifying a painting by artist and style is tricky for humans; spotting the links between different artists and styles is harder still. So it should be impossible for machines, right?

Few areas of academic inquiry have escaped the influence of computer science and machine learning. But one of them is the history of art. The challenge of analyzing paintings, recognizing their artists, and identifying their style and content has always been beyond the capability of even the most advanced algorithms.

That is now changing thanks to recent advances in machine learning based on approaches such as deep convolutional neural networks. In just a few years, computer scientists have created machines capable of matching and sometimes outperforming humans in all kinds of pattern recognition tasks.

Today, we see just how advanced these approaches have become in the hands of Babak Saleh and Ahmed Elgammal at Rutgers University in New Jersey. These guys have used these new machine learning techniques to train algorithms to recognize the artist and style of a fine-art painting with an accuracy that has never been achieved before.

What’s more, the results reveal connections between artists, and between entire painting styles, that art historians have labored for years to understand.

Saleh and Elgammal begin with a database of images of more than 80,000 paintings by more than a 1,000 artists spanning 15 centuries. These paintings cover 27 different styles, each with more than 1,500 examples. The researchers also classify the works by genre, such as interior, cityscape, landscape, and so on…

  • BillyHW

    The algorithm probably doesn’t complain about the minimum wage either, or whether her benefits plan covers the pill.

  • Uncle_Waspy

    It’s incredible to think of all the vocations rendered obsolete by technology. Cabbies and truck drivers can kiss their jobs goodbye. Tool and die. Hamburger flippers and art restorers too.

    Prostitutes better not get too complacent either, because their replacements are just a few years away.

    The thing is…….who is going to pay for these products and services if everybody is unemployed?

    • Petey

      the “point” presumably of machines, robots, technology in general, is to help humanity. Arguably, other reasons too, like knowledge for knowledge’s sake. But the principal one is utilitarian. If technology of some sort – AI or whatever – starts interfering with human well-being and happiness, it’s time to consider revising or scrapping it.

  • Zaba

    Is there potentially some irony here?

    Today, we see just how advanced these approaches have become in the hands of Babak Saleh and Ahmed Elgammal at Rutgers University in New Jersey.

  • Brett_McS

    Reading medical scans (X-rays, MR etc) is another area where machines can perform better.

  • Kaye

    Maybe this will enable them to make up some sort of objective criteria for evaluating “creativity” – or have AIs make them up. So the machines will end up (objectively) judging art, music, etc – essentially deciding what beauty and ugliness are, based on objective (to the unemotional machines) criteria.

    But I personally tend to find these sorts of stories, though interesting, rather depressing. If nothing else, it speaks to the complete unimportance and weakness of humanity, and to the essential worthlessness and meaninglessness of human creativity, whether it is art or anything else: a machine can always do it better and faster. Art and creativity are not “inspiration” – not emotional/spiritual – but a matter of numbers, mathematical symmetry, logical patterns, all of which can be duplicated (in superior fashion) by a machine. Humans can no longer full themselves that they are anything but utterly inconsequential.