WILL COMPUTERS BECOME PERFECT ART FORGERS?
The choice of artist was no coincidence. “Rembrandt completed a lot of paintings, so there’s a huge amount of technical data available,” explains Joris Dik of Delft University of Technology. Computers can only learn the style of particularly productive artists – and even then they’ll not be 100% perfect. Certain details, like the reflected light from the collar onto the chin, are missing from the image. “Still,” explains art historian Gary Schwartz, “the technique could help unmask forgeries from newly discovered paintings.” Future software would compare all ‘real’ noses painted by Rembrandt with the structure of the new one and evaluate their similarity.
WORKS OF ART MADE FROM DATA This ‘man in the hat’ brings together more than 168,000 image details from hundreds of Rembrandt paintings. It’s not just a simple flat image either; depth and texture was added to create a bona fide three-dimensional model (see below). The image was painted using a 3D printer that used 13 layers of ink. 0.05mm 0.1mm 0.18mm 0.2mm MOUNTAINS OF COLOUR Regardless of whether it’s printed or painted, every brushstroke creates peaks and valleys on the canvas. Some are so tiny they measure less than one millimetre.