The camera was created by Dan Macnish, an engineer and visual artist based in Melbourne, Australia.
“There is something eternally amusing about a physical, unique image, that is uniquely different to digital,” Macnish writes. “Playing with neural networks for object recognition one day, I wondered if I could take the concept of a Polaroid one step further, and ask the camera to re-interpret the image, printing out a cartoon instead of a faithful photograph.”
After the camera snaps a photo with its digital camera, it uses a neural network and Google data for object recognition. Once the objects in a photo are determined, the camera uses “The Quick, Draw! Dataset” from Google (50 million user-submitted sketches in 345 categories from a game).
Sketches from The Quick, Draw! Dataset
The Raspberry Pi-based camera then prints out its cartoon-ified version of the photo using a thermal printer.
“One of the fun things about this re-imagined polaroid is that you never get to see the original image,” Macnish says. “You point, and shoot – and out pops a cartoon; the camera’s best interpretation of what it saw.
“The result is always a surprise. A food selfie of a healthy salad might turn into an enormous hot dog, or a photo with friends might be photobombed by a goat.”
If you’d like to create your own version of the Draw This camera, Macnish has shared his code and instructions through GitHub.