Bad doodler? Artificial intelligence can fix that too with Google’s AutoDraw

By Hillary K. Grigonis Published December 27, 2017

Say goodbye to crummy stick figures — artificial intelligence can now turn crappy drawings into actual artistic sketches. AutoDraw is a new web-based tool from Google, announced April 11, that interprets quick sketches and replaces them with artistic renderings.

The AI program seeks to recognize what you are drawing, and then displays similar drawings at the top for you to replace yours with. Along with replacing your sketches with artistic renderings, the online tool allows users to color in the figures and add text, good for making quick graphics that don’t look like they were done quickly, from flyers to coloring pages. Since the program is web-based, users can access it from desktop computers or mobile devices — and it’s free.

Recommended Videos

When AutoDraw turns your bad stick figure into a yoga pose, it’s using neural networks and object recognition to determine exactly what you’re trying to draw, then displaying a list of similar figurines crafted by artists. Along with using drawings from a team of artists, the program encourages users to submit their own non-crappy drawings for the system to use.

The tool comes from Google’s experimental AI Quick Draw that was designed to guess exactly what you’re trying to sketch, except the new web-based tool can actually replace it with the real thing. Quick Draw was actually partially taught by asking web browsers to draw an object in under twenty seconds. The more users drew with the program, the better the system got at interpreting just what that drawing is.

The computer verbally guesses what you’re drawing — the first guess on our snowman drawing was a potato, but the system picked it up after the second snowball and even before any carrot noses.

Besides the artificially intelligent sketch recognition, AutoDraw will also let you keep your drawings as-is for those just looking for a free drawing tool. Sketches can then be downloaded or shared on Twitter, Facebook or Google+. Since it’s designed for quick sketches, there isn’t an option to save your work to come back later.

Hillary K. Grigonis

Former Contributor

Hillary never planned on becoming a photographer—and then she was handed a camera at her first writing job and she's been…

Topics

Emerging Tech

Anti-surveillance clothing is getting cheaper, but don’t expect an invisibility cloak

Affordable shirts now claim to confuse facial recognition, although their protection depends heavily on the camera and software watching you

Chart, Plot, Adult

Anti-surveillance clothing is starting to look less like an art-school experiment and more like something you could actually wear outside. Shirts designed to confuse facial recognition systems now cost about as much as ordinary streetwear, although buying one won’t make you disappear.

The Guardian reports that designers are using face-like prints, unusual cuts and infrared lights to interfere with computer vision. These techniques target specific weaknesses, so their success depends on what happens to be watching you.

Emerging Tech

This spinning drone hides in plain sight using a visual illusion

This drone doesn't turn invisible. It tricks your brain into thinking it has.

Phantom Twist

For decades, engineers have chased the dream of an invisible drone. The usual approaches have involved transparent materials, camouflage coatings, or complex optical systems that bend light around an object. Researchers at Northwestern University decided to take a completely different route. Instead of hiding the drone itself, they chose to fool the human eye.

The result is Phantom Twist, an experimental drone that spins so rapidly it almost disappears into the background. It's not technically invisible, but to anyone watching, it looks more like a faint blur than a flying machine.

Emerging Tech

This smart knitted fabric can flip switches, count your steps, and even change shape

Grandma's knitting just entered its Iron Man era

Representative Image

For most of us, knitting brings to mind sweaters, scarves, and perhaps an ambitious grandmother determined to make winter more fashionable. Researchers at Harvard University, however, have a far more futuristic vision. They've transformed ordinary knitted fabric into a programmable material capable of changing shape, acting as an electrical switch, sensing movement, and potentially forming the foundation of tomorrow's wearable technology.

The research, published in Advanced Functional Materials by scientists at the Harvard John A. Paulson School of Engineering and Applied Sciences (SEAS), demonstrates how machine-knitted textiles can "snap" between multiple stable shapes without relying on motors or rigid mechanical parts.