This robot that can instantly find Waldo might be my favorite use of artificial intelligence yet

Advertisement
This robot that can instantly find Waldo might be my favorite use of artificial intelligence yet

Advertisement
where's waldo robot ai

YouTube/redpepper

If you can't find Waldo in this image in less than 5 seconds, you can't beat "There's Waldo."

  • Everyone loves a good "Where's Waldo?" puzzle - unless you can't actually find Waldo, then it starts to get frustrating.
  • Don't feel too bad: One company actually built a robot that can find Waldo faster than most humans probably could.
  • The robot, called "There's Waldo," uses computer vision and machine learning to spot Waldo - it's been able to find the hidden character in as little as 4.5 seconds.
  • Here's how "There's Waldo" works:

Get the latest Google stock price here.

{{}}

Creative agency redpepper built a camera-mounted robotic arm and connected it to Google's machine learning service AutoML, which analyzes the faces on any given page to find Waldo.

Creative agency redpepper built a camera-mounted robotic arm and connected it to Google's machine learning service AutoML, which analyzes the faces on any given page to find Waldo.

If "There's Waldo" can find a face in the puzzle with 95% confidence or higher, it will move its mechanical arm to point at any and all Waldos on the page with its creepy rubber hand.

If "There's Waldo" can find a face in the puzzle with 95% confidence or higher, it will move its mechanical arm to point at any and all Waldos on the page with its creepy rubber hand.
Advertisement

The robot arm, which is controlled by a tiny Raspberry Pi computer, was coded with Python to extend and take a photo of the "Where's Waldo" puzzle.

The robot arm, which is controlled by a tiny Raspberry Pi computer, was coded with Python to extend and take a photo of the "Where's Waldo" puzzle.

Once the photo of the puzzle's been taken, the OpenCV computer vision service finds and separates all of the faces it can find on the page.

Once the photo of the puzzle's been taken, the OpenCV computer vision service finds and separates all of the faces it can find on the page.
Advertisement

At that point, those faces are sent off to Google's Cloud AutoML vision service, which compares each photo against its trained model of what Waldo looks like.

At that point, those faces are sent off to Google's Cloud AutoML vision service, which compares each photo against its trained model of what Waldo looks like.

Google's Cloud Auto ML service, which doesn't require any coding experience to use (it's free to try), was trained to find Waldo by looking at dozens of pictures of the cartoon, which were all found on Google Image Search.

Google's Cloud Auto ML service, which doesn't require any coding experience to use (it's free to try), was trained to find Waldo by looking at dozens of pictures of the cartoon, which were all found on Google Image Search.
Advertisement

If the service returns a match with confidence of 95% or higher, the robot arm is programmed to extend to the exact location of the face that matches Waldo, and point to it.

If the service returns a match with confidence of 95% or higher, the robot arm is programmed to extend to the exact location of the face that matches Waldo, and point to it.

redpepper says "There's Waldo" is only a prototype, but it's able to find Waldo on any page in as little as 4.45 seconds.

redpepper says "There's Waldo" is only a prototype, but it's able to find Waldo on any page in as little as 4.45 seconds.
Advertisement

Check out There's Waldo in action below.

Next StoryHow to cancel subscriptions on your iPhone