AI identifiziert Künstler anhand eines Pinselstrichs

Wenn ich hier über Illus oder Malerei schreibe, benutze ich oft das Wort „Strich“: Picassos Strich war proportional-verschoben und schwungvoll, Bill Watterssons Strich wirkt fragil aber kräftig, Mike Mignolas Strich ist sort-of-brutalistisch und so weiter. Der „Strich“ eines Illustrators ist seine Handschrift im Kontext einer Zeichnung.

Jetzt haben Wissenschaftler AIs genau auf diesen „Strich“ trainiert: Ein Neural Network trainierten sie auf die Eigenschaften des künstlerspezifischen Strichs (Picasso = „proportional-verschoben“, „schwungvoll“), und ein weiteres NN, um diese Eigenschaften in einem einzigen Strich zu bewerten („Dieser Strich von Picasso ist zu 80% proportional-verschoben und 60% schwungvoll“).

Damit können sie nun nicht nur Künstler anhand eines einzigen Pinselstrichs identifizieren (mit 80% Erfolgsquote), sondern in Kombination konnten die AIs auch Fälschungen anhand eines einzigen Striches in der Zeichnung feststellen – in 100% aller Fälle.

Technology Review: This AI Can Spot Art Forgeries by Looking at One Brushstroke

In a new paper, researchers from Rutgers University and the Atelier for Restoration & Research of Paintings in the Netherlands document how their system broke down almost 300 line drawings by Picasso, Matisse, Modigliani, and other famous artists into 80,000 individual strokes. Then a deep recurrent neural network (RNN) learned what features in the strokes were important to identify the artist.

The researchers also trained a machine-learning algorithm to look for specific features, like the shape of the line in a stroke. This gave them two different techniques to detect forgeries, and the combined method proved powerful. Looking at the output of the machine-learning algorithm also provided some insight into the RNN, which acts as a “black box”—a system whose outputs are difficult for researchers to explain.

Since the machine-learning algorithm was trained on specific features, the difference between it and the RNN probably points to the characteristics the neural network was looking at to detect forgeries. In this case, it was using the changing strength along a stroke—that is, how hard an artist was pushing, based on the weight of the line—to identify the artist. With both algorithms working in tandem, the researchers were able to correctly identify artists around 80 percent of the time.

The researchers also commissioned artists to create drawings in the same style as the pieces in the data set to test the system’s ability to spot fakes. The system was able to identify the forgeries in every instance, simply by looking at a single stroke.