The general idea of Facebook photos can be a double-edged sword.
It’s a great way to keep up with friends and family — from travel experiences and funny moments, to new babies — while on the other hand, we’ve all got those friends who post everything… (i.e. I love photos of new babies, but maybe wait at least a few minutes before you post that moment of glory.)
At some point, you’ve probably remembered or thought about an old photo that you just wanted to look back on or show off to someone — but you can’t remember when it was or even who posted it.
So while your news feed is flooded with TMI photos, finding the ones you actually want to see is kind of a nightmare process. In fact, you would have to search using specific terms and text that were either tagged in the photo post or included in the caption.
Read more: Beware of Facebook customer service scam
Facebook announces new features that make finding photos much easier
Facebook just announced a new feature that will allow users to search and easily find specific images among their friends’ photos.
The social media giant says its artificial intelligence (AI) can now ‘do things like recognize what’s in an image, what type of scene it is, if it’s a well-known landmark, and so on,’ the company said in a statement. ‘This, in turn, helps us better describe photos for the visually impaired and provide better search results for posts with images and videos.
So how does it work?
The teams over at Facebook have done a lot of research into ways the website can better understand images and videos that are posted to the platform, including ways to improve user experience for people who are visually impaired.
The company says this has allowed it to ‘make big improvements in image classification — questions like ‘What is in the image?’ and ‘Where are the objects?’ are being answered by systems more accurately than ever. We’ve advanced this research by designing techniques that detect and segment the objects in a given image.’
So users will now be able to find specific photos based on what the system ‘sees’ in an image — even if the post doesn’t include that specific text in the tag or caption.
Using this technology, Facebook says ‘photos pass through a deep-learning engine that can segment the image and identify objects and scenes, and attach even more meaning to the photo.’
In other words, in a search for “black shirt photo,” the system can “see” whether there is a black shirt in the photo and search based on that, even if the photo wasn’t tagged with that information.
So instead of digging through all of your friends’ old photos when you can’t remember exactly when or who posted that picture you’re looking for, Facebook says the new search system will do it for you by sorting through the information and then surfacing the most relevant photos.
To find the most relevant search results, the company says it used ‘cutting-edge deep learning techniques to process billions of photos and understand their semantic meaning.’
How accurate will the new feature really be in the real world? Guess we’ll find out — so stay tuned. You can see more details from Facebook here.