The computer says that there is an 80.58% probability that the painting is a real Renoir | Frame

Staring enigmatically at an invisible object to her right, the raven-haired woman bears a striking resemblance to the person depicted in Pierre-Auguste Renoir’s painting. gabrielawhich Sotheby’s recently valued at between £100,000 and £150,000.

However, art connoisseurs disagree on whether the work, which belongs to a private Swiss collector, is real. Now, artificial intelligence has stepped in to help settle the dispute, and the computer has judged that it’s probably a genuine Renoir.

AI is increasingly being used to help decide whether valuable works of art are real or fake. Earlier this month, Art Recognition, the Swiss company that developed the technology, announced that it had concluded that Switzerland’s only Titian, a work titled Evening Landscape with a Couple, held by Kunsthaus Zürich, was probably not painted. by 16th century Venetian artist.

However, art connoisseurs have warned that the AI ​​is only as good as the paintings it is trained on. If they are fake or contain areas that have been airbrushed, it could create even more uncertainty.

Art Recognition was contacted about Renoir, titled Portrait de femme (Gabrielle), after the Wildenstein Plattner Institute, one of two institutes that publishes a comprehensive list of all of Renoir’s known works of art, known as catalogs raisonnés – he refused to include it in his list.

The company used photographic reproductions of 206 authentic paintings by the French Impressionist to teach its algorithm about his style, which to human observers is characterized by broken brushwork and bold combinations of complementary colors. To increase accuracy, he also divided the images into smaller patches and showed them to the algorithm, as well as training it on a selection of paintings by artists with a similar style who were active around the same time as Renoir.

Based on this assessment, he concluded that there was an 80.58% chance that Portrait de femme (Gabrielle) It was painted by Renoir.

Carina Popovici, executive director of Art Recognition, believes that this ability to put a number to the degree of uncertainty is important. Speaking at a meeting on the use of forensic science and technology in the art trade at the Art Loss Register in London on Monday, he said: “Connoisseurs often tell art owners that it is their ‘impression’ or ‘gut feeling’ that a painting is genuine or not, which can be very frustrating. They really appreciate the fact that we are more precise.”

Encouraged by this result, the painting’s owner approached another Parisian think tank, GP.F.Dauberville & Archives Bernheim-Jeune, which publishes its own catalogs raisonné of works by Renoir. After requesting a scientific analysis of the painting’s pigments, they also concluded that it was a genuine Renoir.

Dr. Bendor Grosvenor, art historian and presenter of BBC Four’s Lost Masterpieces of Britain, worried that such technologies could devalue the contribution of experts in assessing a work of art’s authenticity.

“So far, the methods used to ‘train’ AI programs, and the fact that they say they can judge an attribution just from an iPhone photo, is not impressive,” he said.

“The technology is especially weak in its inability to account for a painting’s condition: many old master paintings are damaged and disfigured by layers of dirt and paint that, without forensic inspection, make it difficult to discern what is and what is not original.

“If some human art appraiser offered to give a ‘certificate of authenticity’ costing thousands of dollars based on nothing more than an iPhone photo and partial knowledge of an artist’s work, they’d be laughed at.”

Popovici agreed that the quality of the training data set was vital, saying they went to great lengths to ensure they only used photographs of authentic works of art. So far, they have trained their AI to recognize about 300 artists, including most French Impressionist and Old Master painters.

“We understand that insiders may feel threatened by this technology, but we are not trying to get them out of the way,” Popovici said.

“We really want to give them the ability to use this system to help them make a decision, maybe in cases where they’re not so sure. But for that to happen, they have to be open to this technology.”

Julian Radcliffe, president of the Art Loss Register, which maintains the world’s largest private database of stolen art, antiquities and collectibles, said: “Artificial intelligence has an increasing role in helping to authenticate art, but it must be allied to the expertise of connoisseurs who specialize in the artist, well-established science such as pigment analysis and provenance research.

“Your advantage lies in your ability to give yes/no answers, for example, pattern analysis or matching, and you are constantly improving, but your work must be interpreted by a human being who must have asked the right question.

“The quest for absolute certainty in authentication has not been reached, and it may never be reached, but we are getting close.”

Leave a Reply

Your email address will not be published. Required fields are marked *