Header Ads

The new NOVEL 3D Facial recognition system – Enhance Security





Image result for The new NOVEL 3D Facial recognition system – Enhance Security

Scientists have developed a new 3D facial recognition system that can improve security measures while potentially removing the need for personal passwords.

Researchers from the University of Western Australia created the first-of-its-kind model –called FR3DNet –analysing 3.1 million 3D scans of more than 100,000 people.
They trained, the new model to learn the identities of a large dataset of ‘known’ persons and then match a test face to one of those identities.

Facial recognition is fast becoming the tool of choice for surveillance, security and IT industries and relies on the ability of computer models to determine whether or not the person is legitimate.


Image result for The new NOVEL 3D Facial recognition system – Enhance Security

Currently, 2D facial recognition of photographs is widely used and has seemingly surpassed human accuracy levels however it has several shortcomings that the more advanced 3D model is able to address.

Unlike 2D face recognition software, 3D models have the potential to address changes in facial texture, expression, poses and scale, yet the data is difficult to gather. 2D facial data can be obtained simply by searching the internet while 3D facial data requires physical collection from real subjects thereby limiting its use.


Image result for The new NOVEL 3D Facial recognition system – Enhance Security


HOW DOES FACIAL RECOGNITION WORK?

Facial recognition identifies people by analyzing the shape of person’s face. Each face has approximately 80 unique nodal points which distinguishes one from another.

The cameras measure distance between various points on the human face, such as width of the nose, depth of the eye sockets, distance between the eyes and shape of the jawline.

These details are being picked up by cameras that use highly speed infrared lights which can also pick out shape in space in space. This means they can pick up finer details like blemishes and wrinkles which cannot be picked by 2D cameras.
     
      Researchers at the Bristol Robotics Laboratory say they are currently getting 95 percent (%) accuracy from the cameras –which they hope will increase further in the coming years.



Related image



The 3D model’s creator Syed Zulqarnain Gilani said the model was a huge step forward in the field of 3D facial recognition. “With off-the-shelf3D cameras becoming cheap and affordable, the future for pure 3D face recognition does not seem far away,” Gilani said.

“Our research shows the recognition performance on 3D scans is better and more robust. Your 3D scan could be in any pose, wearing glasses or a face mask, and laughing or just smiling and the deep model can recognize you in an instant,” he said.

Image result for The new NOVEL 3D Facial recognition system – Enhance Security


“We hope that this research will help improve security on devices that use facial recognition to grant access to networks and systems,” he added.










No comments:

Powered by Blogger.