On Thursday, Microsoft announced the launch of a new Garage app that can identify dog breeds from a photo.
"Man’s best friend has inspired a new app – Fetch! Using your iPhone camera or photo library, it can identify and classify dogs by breeds and tell you what kind of human personality fits best with specific breeds," said Microsoft in a blog post on the new app. Fetch! was developed by the Microsoft Garage team, ahead of the American Kennel Club’s Meet & Compete and the Westminster Kennel Club Dog Show. "There was an interest in creating a framework that would allow you to take a domain – in our case, dogs – and recognize numerous classes, such as breeds. We were interested in enabling an app to allow you to make object recognition extraordinary, fun and surprising," said Mitch Goldberg, a development director at Microsoft Research. "We wanted to bring artificial intelligence to the canine world. We wanted to show that object recognition is something anyone could understand and interact with." Goldberg and his Cambridge, U.K based team built the app; the team works on user experience, machine learning, computer vision, and intelligent cloud services.
While Fetch! was made for the canine world, the app has a "hidden fun mode" that will match people with dog breeds. "If you want to take photos of dogs, it will tell you what dog breed it is, if it's one of our supported breeds," Goldberg says. "If I choose to take a photograph of a flower, it’ll say, 'No dogs found! Hmmm… This looks more like…flower?' But if you take a picture of a person, it’ll kick into its hidden fun mode. And in a playful way, it'll communicate to you not only what type of dog it thinks you are, but also why. It's fun to see if the app knows it's not a dog. A lot of the time, it'll tell you what that image is." If the app is unable to identify a dog's breed, it will show a percentage of the closest breed and tapping this percentage will give you the top 5 breeds that could be in the dog. Fetch! is available as an app from the Apple App Store and online at What-Dog.net.
Photo: © iStock.