Facebook might have discovered a new innovation that can identify an individual, even in the absence of their faces.

Currently, the website has a feature that automatically suggests a tag to a specific person based on their faces; however, according to Business Insider, this feature may finally get an upgrade through other identifiers such as frequently worn clothes, posture and even an individual's own significant haircut.

Like Us on Facebook

Although tests are still being performed for the new innovation, the software team claims it already has 83 percent accuracy rate in identifying an individual from a photo uploaded on the website.

Although tests have been made with around 40,000 pictures, there are still lots of work compared to the total number of pictures stored on the website's servers, amounting to at least 250 billion photos in total. In a statement said by Facebook's Artificial Intelligence head, it said, "There are  lots of cues we use, people have characteristic aspects, even if you look at them from the back.. for example, you can recognize Mark Zuckerberg very easily because he always wears a gray T-shirt." Facebook's "Moments" feature allows a faster way to share a photo by tracing the individual and suggesting to send it to the person.

The Moments app allows you to sync your phone and send different pictures to people who matches the identity on your photos. The same thing can happen where you can receive your own photos via the synced images. This private way of sharing photos has enabled users to quickly share photos without exposing them publicly during transfer. It will be the absolute solution in acquiring all your photos from your friends and vice versa.

According to the New Scientist, the said feature also raised some privacy concerns as it claims that it can also identify a person even if they are not looking at the camera. Ralph Gross of Carnegie Mellon University, who admitted that the algorithms were in fact impressive, said "If, even if you hide your face, you can be successfully linked to your identification, that will certainly concern people. Now is the time to discuss this important questions."

TagsFacial Recognition, facebook facial recognition