University of California, Riverside researchers have embarked on a study to determine if facial recognition software can identify unknown subjects in historical works of art. With an initial grant of $25,000 from the National Endowment for the Humanities, they will attempt to adapt facial recognition tech to account for the idiosyncrasies unique to 2D portraits. To start, they will compare the death or life mask of a known person to a sculptural portrait of the same person (a "3D-to-3D" test), then compare subjects across 3D and 2D mediums. If those tests are successful, the team will test portraits of known people against unidentified portraits.
UC Riverside professor Conrad Rudolph explains that "technology that 'reads' human faces already must content with variations in facial expressions, age, facial hair, angle of pose, and lighting," and that "refining that technology to recognize human faces in two- or-three dimensional art introduces further challenges." But, if successful, the tech could provide interesting historical insights. Rudolph says that "these portraits are social documents" that can help fill in social history, like, for example, "a previously unknown connection between a nobleman and religious or political leaders of the time." The team obviously still has a lot of work to do, but it certainly sounds like a novel way to use new tech to solve old mysteries.