Good Thinking

Computer creates high-tech Rembrandt counterfeit

Computer creates high-tech Rem...
The results of hours of analysis, algorithms and art history
The results of hours of analysis, algorithms and art history
View 5 Images
The results of hours of analysis, algorithms and art history
1/5
The results of hours of analysis, algorithms and art history
Individual facial components were also analyzed
2/5
Individual facial components were also analyzed
Then, it was necessary to figure out the correct proportions for arranging those components
3/5
Then, it was necessary to figure out the correct proportions for arranging those components
In creating the new work, various traits of Rembrandt's paintings were studied such as the age and ethnicity of his subjects
4/5
In creating the new work, various traits of Rembrandt's paintings were studied such as the age and ethnicity of his subjects
Finally, a height map was created so that a 3D printer could mimic the way Rembrandt laid his paint down on canvas
5/5
Finally, a height map was created so that a 3D printer could mimic the way Rembrandt laid his paint down on canvas
View gallery - 5 images

In conversations about artificial intelligence and the time when machines will be able to functions as well as — or better than — human beings, it's often said that one thing computers will never be able to do is create art and music the way we do. Well, that argument just lost a bit of steam thanks to a project that's been carried out by Microsoft and ING. Working with the Technical University of Delft and two museums in the Netherlands, the project, called "Next Rembrandt," used algorithms and a 3D printer to create a brand-new Rembrandt painting that looks like it could easily have been delivered by Dutch Master's own hand about 350 years ago.

To create the new painting, the team of experts used computer software and a deep learning algorithm to analyze 346 of Rembrandt's paintings. In addition to studying components of his work, such as how he drew an eye or how faces were proportioned, the project also included an analysis of the height of the paint from the surface of the canvas.

Because Rembrandt produced more portraits than any other kind of painting, the group decided to focus its efforts on that type of artwork — particularly, those created from the years 1632-1642, when he painted the largest number of them. After using software to analyze the portraits, the computer suggested that the perfect Rembrandt painting to produce would be a portrait of a white man with facial hair aged between 30 and 40. He should also be wearing black clothes and have a collar and a hat, said the analysis.

The next step, and the one that really lies at the crux of the project — and the idea that computers can produce art every bit as good as our revered masters — is that the team developed software that basically decoded how Rembrandt did what he did.

"To master his style, we designed a software system that could understand Rembrandt based on his use of geometry, composition, and painting materials," says the website on which the project is featured. "A facial recognition algorithm identified and classified the most typical geometric patterns used by Rembrandt to paint human features. It then used the learned principles to replicate the style and generate new facial features for our painting."

That means the computer was able to create eyes, a nose, and other facial features by mimicking Rembrandt's style. Then it was time to put those features together.

"An algorithm measured the distances between the facial features in Rembrandt's paintings and calculated them based on percentages," says the site. "Next, the features were transformed, rotated, and scaled, then accurately placed within the frame of the face. Finally, we rendered the light based on gathered data in order to cast authentic shadows on each feature." The rendering process took 500 hours.

Next came the moment for math and machine to do what only skin and bone had once done. Using the paint height map that had been created, a 3D printer laid down 13 layers of ink to create a textured work of art that may as well have been set to canvas by Rembrandt himself.

In the end, the painting took 18 months to create and consists of 148 billion pixels. It is on temporary exhibit at the Looiersgracht 60 gallery in Amsterdam. A permanent home has yet to be announced.

You can deeper insight into the artist, the process by which his style was recreated and the new painting itself on The Next Rembrandt website or through this accompanying video.

The Next Rembrandt

Sources: ING, The Next Rembrandt

View gallery - 5 images
3 comments
Jim Parker
When will this be an add-on for Photoshop?
LaurentiuTodie
It seems like a waste of valuable time and coding. What problem does it solve? It may again spell fear in the hearts of figurative painters, just like photography did once upon a time, but isn't too impressive for a creative mind, in my opinion. That, and Photoshop is bloated already. It doesn't need this kind of function, except maybe for forgers, and I don't think that Adobe caters to them.
habakak
It's naïve to think machines won't be able to create art, especially paintings. Paintings is possibly the easiest form of art for a machine to create because it's about math and precision. And on those 2 fronts humans already can't compete. On the creativity front though humans are still way ahead, but that will also change. There is no reason to believe (besides belief itself) that machines can't one day be cognizant and creative. As humans we tend to think we are special, but as with most of our misbeliefs of the past, we continually learn that most of what we believed is not true. But each generation and society will always have their misbeliefs to trip them up and make later generations wonder in awe about how they could have believed what they believed. Like we look at past generations in disbelief of the things they believed in, like the earth being the center of the universe or solar system, the earth being flat, women not being equal to men, children not being equal to adults, blacks not equal to whites, etc. And until recently (and still in most places in the world) homo and transsexuals not being equal to heterosexuals, etc. No matter how much we evolve, our ancient beliefs will most likely always dominate our value systems.