Visible light facial recognition with deep learning

February 2019 Access Control & Identity Management

ZKTeco has created a unique range of visible light facial recognition products combined with a flexible Android platform. The unique range of products are based on the latest Artificial Intelligence (AI) and Neural Network technologies. ZKTeco’s visible light facial recognition technology has been specifically developed for purposes where high-speed facial recognition at an extremely high level of accuracy is vital.

Unlike traditional facial recognition devices on the market today where face alignment poses as a problem, the ZKTeco visible light facial recognition products use deep learning algorithms to provide true recognition of faces, which enables larger pose angles. By applying 3D rendering through machine learning technology, its products provide pose angle tolerance up to 30 degrees in yaw, pitch and roll axis.

ZKTeco AI visible light facial recognition products make use of a Proactive Facial Recognition technology, which enables users to be automatically recognised by the device while walking past, unlike having to stand steadily in front of a camera. Thus, it is way faster than the previous near IR facial recognition and the recognition distance has been greatly extended to up to 3 metres, which significantly improves maximum traffic rate. Detection of up to five people per second is possible if the facial template is stored locally on the device.

Anti-spoof functionality

With the applied Convolutional Neural Network (CNN) algorithm, anti-spoof function has been greatly enhanced within ZKTeco AI visible light facial recognition products and is able to check fake faces, photos and video attacks. Face feature extraction is based on detecting differences in lighting, texture and resolution and includes two types of tests. Anti-fake photo attack is tested by comparing the background pixel movement and consistency of the detected face’s resolution verses video stream background. With the anti-fake video attack test, the device can detect a face’s texture and resolution, as well as whether the detected face is surrounded by a frame or not.

The ZKTeco AI visible light facial recognition technology is a touchless biometric solution, which is much more hygienic than other biometric technologies. The products use the Android operating system to bring clients the unlimited potential to formulate their own solutions, based on the needs of their end users.

Designed in various structures and sizes, the visible light facial recognition technology is very flexible and can be customised to fit any solution. Whether you are working in a bank, the education sector, a conference setting or the beauty industry, the AI visible light facial recognition platform is versatile.

ZKTeco AI visible light facial recognition technology can either be used as an access control terminal, time and attendance terminal or any other solution can be derived from this platform. For example, the device can be used as an advertisement display panel with biometric analysis on age, gender and even behaviour making it easier for clients to identify their target market. With this technology the Know your Client concept can be derived – users can immediately recognise their regular customers and easily assist them in their needs, making the customers feel special and impressing them with excellent customer service.



Credit(s)




Share this article:
Share via emailShare via LinkedInPrint this page



Further reading:

Enterprise identity fraud prevention
Access Control & Identity Management
Trustmatic brings government-grade facial 1:N search capabilities to the cloud, supporting face deduplication and identification against watchlists, and providing seamless integration via REST API.

Read more...
The AI knows best
Access Control & Identity Management
RBA makes use of the vast computing power of machine learning to analyse thousands of data points to determine how risky a transaction may be.

Read more...
ZKTeco Experience Centre
ZKTeco News Access Control & Identity Management
ZKTeco South Africa has opened the doors to its innovative and interactive space, the ZKTeco Experience Centre in Centurion, Pretoria and welcomes visitors to partake in the ‘Powered by ZKTeco’ experience.

Read more...
ZKTeco
ZKTeco Products
ZKTeco’s biometric security technology is aimed at overcoming shortcomings of previous facial recognition terminals and achieve an all-rounded upgrade on performance and reliability by using deep learning. ...

Read more...
Touchless school access control
neaMetrics Suprema Editor's Choice Access Control & Identity Management Integrated Solutions Education (Industry) Products
Wolverhampton Grammar School deployed a Suprema access control solution, integrated with Paxton to resolve its legacy access control challenges.

Read more...
Visible light facial recognition
ZKTeco Access Control & Identity Management
The ZKTeco SpeedFace-V5L [TI] is a fully upgraded version of the SpeedFace-V5L [TD] visible light facial recognition body temperature detection terminal, supporting facial and palm recognition.

Read more...
Upgraded ProFace product line
ZKTeco Products
The ZKTeco ProFace X [TI] is powered by the ZKTeco-customised CPU for running its intellectualised engineering facial recognition algorithm and the latest computer vision technology.

Read more...
Smart, efficient and green
Salto Systems Africa Access Control & Identity Management
Battery life and seamless use is particularly important in an electronic access control solution that relies on battery-operated locks.

Read more...
Over 50% growth in use of digital documents between 2022 and 2026
Access Control & Identity Management Security Services & Risk Management
The number of users of digital identity documents is expected to exceed 6,5 billion globally in 2026, enabling rapid advances in eGovernment services.

Read more...
Touchless access to education
ZKTeco Education (Industry)
Visible light facial recognition technology gives one an endless platform to create a full security system without people, especially intruders, having knowledge of them being monitored.

Read more...