Google has filed a patent for facial recognition technology that will compete with Apple's Face ID — with a particularly interesting twist.
-
Facial recognition technology is found in nearly every modern smartphone.
It serves as a convenient and fast biometric authentication method for a variety of actions, from unlocking the screen to making payments online.
But despite their surface similarities, there is a fundamental difference between 2D and 3D facial recognition.
-
Two-dimensional recognition uses a camera to capture the user's face and analyzes the image with an algorithm to identify the person in the photo.
This technology is inexpensive to use and implement, since it requires no additional hardware beyond the device's built-in selfie camera.
On the other hand, it can be fooled relatively easily using a photo of the phone's owner, and it struggles to function in the dark.
-
Three-dimensional recognition is found primarily in Apple devices, where a dedicated hardware component projects 30,000 infrared dots onto the user's face and analyzes the returning light pattern to create a depth map.
The facial recognition capabilities on Apple devices are impressive — the system works well even in complete darkness, across different environments, and with glasses, a hat, or even a beard.
-
In its patent filing, Google aims to build a 3D facial recognition system positioned directly beneath the phone's display.
Some of the screen's pixels would be transparent to light coming from below, allowing the system to operate without adding any hardware component alongside the selfie camera.
The drawback of this technology is that it could significantly increase the cost of displays and the cost of repairing them.
-
Zooming out, the patent can be seen as building on another Google patent — an under-display selfie camera.
The advantages of an under-display camera are twofold: it avoids creating a "notch" at the top of the screen, and it improves image quality by using the display glass as a light filter for the camera.
The vision combining both patents is a remarkably innovative smartphone that would offer a high-quality selfie camera and 3D facial recognition, together with a true edge-to-edge, full-screen display.