A food selfie of a nutritious salad turns into a giant hot dog, or a photo of your friends suddenly includes a barn animal: Snap a shot using this DIY, Polaroid-inspired camera, and a machine learning algorithm will interpret what it thinks it sees into a doodle drawing.
Dan Macnish, a Melbourne, Australia-based engineer and artist, writes on his blog that the camera combines a neural network for object recognition, the Google Quick Draw dataset, a thermal printer, and a Raspberry Pi. Using Google’s pre-trained models in TensorFlow, plus the Quick Draw dataset of 50 million simple doodles across 345 categories, he was able to code the camera to attempt to translate whatever he pointed it at into a drawing.
“Attempt,” because the AI doesn’t always doodle its subject as you’d expect.
“One of the fun things about this re-imagined polaroid is that you never get to see the original image,” Macnish wrote on his blog post about the project. “You point, and shoot—and out pops a cartoon; the camera’s best interpretation of what it saw.”
If selfies translated into hot dogs using instant cameras and AI sounds like a good time to you, Macnish put the complete instructions on Github, so you can make your own.