Yelp has begun an image-recognition project, with an end goal of getting computers to identify what’s in the photos posted to a business’ Yelp page, Wired reported in October.
This means the photos on your Yelp profile could increasingly become more important as Yelp works on its first project regarding image recognition. The project will focus on bringing the best photos to the front of a Yelp page in order to give consumers the best possible impression of a business, offering a glimmer into the future of online reviews.
“We’re trying to figure how can we bubble up the best photos, the photo that’s going to make you take that risk,” said Frances Haugen, senior project manager at Yelp, in an interview with Wired. “The photo that’s going to let you go to that new hair stylist, or let you pick that wedding venue, or pick the restaurant to take a friend out to their birthday dinner.”
Computers will first need to learn how to tell the difference between two different photos – such as a dark photo of the interior of the restaurant and a vanilla milkshake – in order to show users the best Yelp photos for a particular business. But automatically surfacing the best photos to the front of a Yelp page is just a start.
For instance, if a consumer is looking for a restaurant with high-top tables in a tropical restaurant, it could take a long time navigating through photos on different Yelp pages. Haugen’s team is working to find a way for computers to index photos with specifics items in them, like high-top tables.
As another example, Haugen told Wired her neighbor’s wife is in a wheelchair and looked through photos to see if a business was wheelchair accessible.
“He used to look through hundreds of photos trying to see what the inside looks like so he could find out if it would be wheelchair friendly,” Haugen said.
“If a computer could figure out which photos have wheelchairs in them, then Yelp could identify wheelchair accessible businesses, automatically.”
This idea is not new. Google, Facebook and of course, law enforcement agencies – as the Wired article points out – have been working on finding a way to recognize faces for years. Even more, a startup called Orbital Insight has been researching a way to find out how much oil there is left on Earth by using photos, Wired reported in March.
The idea of using photos to figure out different aspects of information is called, “deep learning,” a form of artificial intelligence.
Similarly, on Nov. 3, Facebook introduced an artificial intelligence demo of their system dubbed Visual Q&A, which lets people receive audible answers after asking questions regarding a photo.
“Think of what this might mean to the hundreds of millions of people around the world who are visually impaired in some way,” wrote Mike Schroepfer, Facebook’s chief technology officer, in a blog post. “Instead of being left out of the experience when friends share photos, they’ll be able to participate. This is still very early in its development, but the promise of this technology is clear.”