. home.aspx



LG CNS upgrades its gate security system with facial recognition

February 11, 2020 / Sujata Bondge

  • LG CNS has deployed an AI-powered, facial recognition gate control service at its Seoul headquarters.

  • It is used in offices instead of the IC cards that employees can use it to enter and exit.

  • LG’s Facial Recognition Gate recognizes the user's face to confirm his or her identity and allow in or out.

Recently, LG CNS has deployed a facial recognition gate control service that runs on artificial intelligence (AI) software at its headquarters in Seoul, the company has announced.

More than our signature, fingerprint or even voice, our face is the most fundamental form of identification. With technology now able to capture, analyze and compare data about the distance between forehead and chin, or the contour of our eye sockets, the application of facial recognition is taken very personally. And rightly so. In the online economy, where activity happens remotely, reliable authentication and identification can be hard to achieve. An email is not a failsafe proof of identity, people forget passwords and PINs, which is why attention has turned to biometric alternatives and the potential of facial recognition.

LG CNS’s facial recognition solution on gates is made in collaboration with Chinese AI firm SenseTime. It uses a designated reader that can identify a face, authenticate an employee, and open the gate. The process completes within just 0.3 seconds, according to LG CNS.

Naturally, the Facial Recognition Gate deals with things like changes in hairstyle and glasses. There are also things like cosmetics and time-related changes, such as wrinkles and blemishes. Even with these differences, the system has to definitively confirm that it is 'this person' without a doubt. On the other hand, when there is another person who has an extremely close appearance, the system has to distinguish between the two and confirm that it is 'another person.

LG CNS facial recognition system is able to achieve a high-performance Facial Recognition Engine with a high level of accuracy. The company added that the facial recognition gate has an accuracy of over 99% and can identify faces two meters from its reader even if the person wears a mask, glasses, make-up, or positions their heads at an angle. The company claims that,

“With 99% accuracy rate, a masked employee looking at their smartphone as they are passing by the gate will still be identifiable.”

Gate control services take considerable time in identifying the person and to avoid this LG came with a solution. Unlike other gate control services, employees will not have to stop or be required to use access cards, fingerprints, or iris scans that consume time. Instead, they can walk right in without slowing down or stopping. All that will be required for the solution to begin operations is for employees to be registered into the system, which entails the uploading of ID photos and consent. For security concerns, all personal information will be stored in the reader and the system.

“Up to 50,000 pieces of facial data can be saved on each reader and it can also be operated without access to the internet.”

The new facial recognition solution has already been deployed in 26 gates so far at LG CNS's headquarters, with the company hoping to eventually expand the new gate control service to up to 27,000 access points operated by LG CNS for 170 of its domestic and global clients.

Prior to this new gate service of facial recognition, the company used gates that automatically issued cards for processing visitors. The Korean IT service firm also has plans to work alongside SenseTime to apply AI technology to CCTVs as well, it added.

Of all the biometric options, facial recognition has attracted the most excitement – especially because of recent advances in the technology.

Early systems struggled in low-light conditions. Spoofers could trick them with photographs and videos. Now, that has changed. Today’s systems use technology such as 3D mapping to achieve live biometric authentication and deliver compelling levels of accuracy.

Because of this, smartphone and tablet makers now use facial identification as the default ‘unlock’ method for their devices and services.

Given the benefits facial recognition offers, it seems only a matter of time before companies large and small, start converting to similar solutions with new techniques. But also facial recognition comes with security issues.

Earlier Panasonic designed Facial Recognition Gate to streamline the departure and arrival processes of Japanese nationals, based on the concept of a simple, secure, and safe solution where both first-timers and the elderly can pass through the gate without delay, frustration, or confusion.