Most cameras are designed to capture scenes as faithfully as possible, but don’t tell that to Dan Macnish. He recently built an instant camera, Draw This, that uses a neural network to translate photos into the sort of crude cartoons you would put on your school notebooks. Macnish mapped the millions of doodles from Google’s Quick, Draw! game data set to the categories the image processor can recognize. After that, it was largely a matter of assembling a Raspberry Pi-powered camera that used this know-how to produce its ‘hand-drawn’ pictures with a thermal printer.
The best part? You never see what the original photo was supposed to look like. You’re putting all your trust in the neural network, and part of the beauty is watching it get things spectacularly wrong. A plant might become a wine glass, or a friend might be reduced to a completely unrecognizable blob. This is more about using AI technology to produce unpredictable art than it is a stab at accuracy.
This article originally appeared on Engadget.
