We take photographs as a way to freeze moments in time and to capture the details that get blurred by our unreliable memories. There is little room for interpretation, and this is kind of the whole point.
[Dan Macnish]’s latest project, Draw This, turns reality into absurdity. It’s a Raspberry Pi-based instant camera that trades whatever passed in front of the lens for a cartoon version of same. Draw This uses neural networks to ID the objects in the frame, and then draws upon thousands of images from Google’s Quick, Draw! dataset to provide a loose interpretation via thermal printer. Seems to us like the perfect camera to take to DEFCON (or any other part of Las Vegas).
If you have a Raspi3, a v2 camera, and a thermal printer, you can make your own crowd-sourced, cartoonified memories using the code in [Dan]’s repo. Still into recording reality? You can use Pi cameras to see in the dark or even explore a body of water.
One of the coolest things I have seen here in a while. There are so many facets to this project from the AI, to the cardboard housing. Nicely done.
I’d like to see the original images for comparison.
> cartoon version of same. Draw This uses neural networks
Got some typos here.
Reminds me of https://hackaday.com/2012/04/25/a-camera-that-describes-a-picture-for-you/
Only this time, it’s fully AI! We’ve come a long way in the last half-decade.
now this is a cool project! I would like to see the faces of people when they see the result of their picture being taken. Really an original project!
Man, that quick-draw game is addicting.
You got that right.
quickdraw. thats a name i haven’t heard for a long time… must be macintosh system 6 and older?
Absolute genius.
This is cool… I would love to buld this and add an etch a sketch to the back of the box as an “lcd” viewfinder :-)
Why when I see this do I think I must use it for pornography?
I don’t think you’ll find usable material in the quick, draw dataset, you’d have to train it with your own material. Get to work!