It's not uncommon for people to jokingly compare themselves or other people to animals.
People that are tall have been compared to giraffes. People who have long necks have been compared to horses. The list goes on.
But what if you could get a more accurate reading about what kind of animal you really look like?
Microsoft's new Fetch app uses photos uploaded by users to guess which dog breed the subject of the photo resembles most.
The app was originally intended to help interested users find out a dogs' breeds, providing vital information for dog owners who, for whatever reason, don't know their dog's breed. It can also tell users what human personality traits fit best with specific breeds.
For more fun, the app guesses what kind of dog a person looks most like and sometimes identifies dog breeds that other animals look similar to. However, Fetch usually can tell when a user tries to get a reading on an inanimate object.
“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,” said Mitch Goldberg, a development director at Microsoft Research whose team built the experience. “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. When there’s not a dog, you still want to use it.”
If the new app cannot accurately identify what breed a dog is, it'll yield results showing the top five breeds that could be in the dog. Different pages allow users to find out more information about each of the breeds.
Fetch, which is comparable to projects previously released by Microsoft, like one in which a data system guesses your age based on a photo, was released Thursday, just days before 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,” Goldberg said. “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.”