Facebook uses image recognition technology to accurately determine the content of your photographs. You can view these machine generated captions to know how Facebook sees your own photographs.
When you upload any photograph to your Facebook account, they look at the actual content of the photograph and try to determine what objects and scenes are inside the image. You may not have added any description, yet Facebook can determine what that picture is all about.
Whether you are having a pizza, enjoying the sun on a beach, playing with your dog or spending an evening with friends, Facebook can accurately figure it out from the photo itself. They internally use these machine generated captions to make your pictures more accessible to blind users.
Video Tutorial – Facebook Image Tags
Facebook’s computer vision tags cover multiple concepts including food, objects (e.g., eyeglasses), people’s expression (are they smiling?), sports, nature (sky, mountains), and more. The best part – if you are in a group photograph, Facebook can accurately tell you the exact number of people in the frame.
A Github user has created a Google Chrome extension that takes away all the manual work and overlays the tags on the pictures without you having to hunt inside the developer tool.