Smithsonian Magazine reports that an algorithm, built by Rutgers University computer scientists Babak Saleh and Ahmed Egammal, allows computers to recognize and classify artworks with the reliability (or even beyond the reliability) of art historians.
The MIT Technology Review originally cited the findings. It reports: “In just a few years, computer scientists have created machines capable of matching and sometimes outperforming humans in all kinds of pattern recognition tasks,” and where visual art is concerned, “the results reveal connections between artists, and between entire painting styles, that art historians have labored for years to understand.”
Frankly, as described, the computers aren’t able to do anything above and beyond what historians have always done, though the MIT story does conclude (of course, because it’s MIT) that the algorithm “provides a new and powerful tool for historians to look for influences between artists that may never have been aware of,” and “also allows a new form of art exploration, jumping from one image to another similar one, in a process that is visually equivalent to finding synonyms.”
(image via MIT Technology Review)