IE 11 is not supported. For an optimal experience visit our site on another browser.

Computer learns to make oriental ink paintings 

Comparison of photo and sumi-e painting.
A computer has learned to automatically convert real photos (left) into an oriental ink style called Sumi-e.Tokyo Institute of Technology via

A computer has mastered Sumi-e, a style of oriental ink painting that conveys a scene with just a few, delicate brush strokes.

The accomplishment takes automated image manipulation to a new frontier, according to MIT’s Technology Review, and may open the door for a new photo app to compete with the likes of Instagram.

The challenge Ning Xie and colleagues at the Tokyo Institute of Technology faced was to get a computer to generate natural-looking brush strokes in a repeatable manner.

Previously, researchers have tackled the problem using a so-called dynamic programming approach, but doing so was computationally expensive and only produced a stroke for a specific shape. 

That’s a problem if you want to turn a snapshot of a flower vase on the table into a Sumi-e painting with the touch of a button and do it all again moments later with a picture of your child in a sandbox.

So, Xie’s team used a technique called reinforcement learning, whereby the computer was rewarded when it made nice, smooth lines for a variety of strokes but not when it stroked poorly.

In this way, the computer learned a library full of brush strokes and now calls on them at any time to create a Sumi-e painting. 

The only catch is that humans manually draw contours on a photo that the computer then fills in with strokes.

The technique is explained in a paper posted on and to be presented at the International Conference of Machine Learning in Edinburgh, Scotland.

"The results ... we think are of good quality," Xie and colleagues conclude.

 —  Via Technology Review 

John Roach is a contributing writer for To learn more about him, check out his website. For more of our Future of Technology series, watch the featured video below.