Brace yourself for "DeepFace."  It's Facebook's new facial recognition software the company claims is 97.25 percent accurate in identifying a person in different photographs.

Facebook said it plans to use this new facial recognition technology with a new program that will identify the subject of an untagged image on Facebook with near perfect accuracy. Goodbye, Tags.

DeepFace, however, is still in the research stage and has not been unleashed on Facebook's 1.23 billion users. But that day is coming.

Facebook researchers said humans who look at two faces can identify if they are the same person with an accuracy of 97.53 percent. "DeepFace" program will be able to do the same with an accuracy of 97.25 percent.

Facial recognition software normally works by analyzing the distance between an individual's eyes and nose in both profile pictures and already tagged images. On the other hand, DeepFace will use software to correct the angle of a face in an image, and compare that to a 3D model of an average face.

It then simulates a "neural network" to find a numerical description of the face. If there are enough similarities, Facebook will know if the faces are in fact the same.

DeepFace involves over 120 million parameters "using several locally connected layers without weight sharing, rather than the standard convolutional layers," according to Facebook.

DeepFace was developed by Facebook artificial intelligence analysts Yaniv Taigman, Ming Yang, and Marc Aurelioa Ranzato, along with Lior Wolf, a faculty member at Tel Aviv University in Israel. Their research paper was first published last week in the Massachusetts Institute of Technology's Technology Review.

The team will announce the DeepFace in June at an upcoming computer vision conference. The people involved in the program work for Israeli startup named Face.com that Facebook bought 18 months ago for $60 million.

DeepFace is fueling concerns the software may approach the intrusive levels seen in the Tom Cruise movie, "Minority Report."