ASEAN's Premier News and Eco System Portal for Big Data, IoT and AI

Home > Big news > News > Kneron launches Real Facial Recognition Solutions to unlock entry level and mid-range smartphone
Kneron launches Real Facial Recognition Solutions to unlock entry level and mid-range smartphone
January 11, 2018 News AI analytics big data IoT

 

Kneron, a leading provider of edge Artificial Intelligence (AI) solutions, today launched its Real Facial Recognition solutions to unlock entry level and mid-range smartphones. As long as a smartphone has a front camera[1], through Kneron’s facial recognition software with deep learning technology, it can not only accurately recognize people’s facial features, but also determine whether the face is real or not. It can rule out the risk of using photos and videos to unlock a smartphone within 0.2 seconds, with less than 0.0001 error rate[2]. Additionally, one device can recognize several faces. Kneron’s Real Facial Recognition solutions have been adopted by smartphone manufacturers and will be marketed worldwide through its partner GMobi.

“There are still many security flaws in traditional facial recognition technologies. For example, the smartphones can be unlocked by using photos and videos. In general, to eliminate the risks, other hardware components, such as infrared lenses and high-resolution lenses, must be embedded into the smartphones, and sometimes design changes are required,” said Albert Liu, Kneron’s CEO. “Kneron now provides innovative real facial recognition solutions to unlock entry level and mid-range smartphones. Only through the software update with no need to change hardware design or add other components, users can experience real-life facial recognition with high accuracy and high security.”

“GMobi has professional experience in mobile Internet services for many years. We offer a wide range of advanced services to help customers to update their mobile devices and serve around 250 million end-users worldwide,” said Paul Wu, GMobi’s CEO. “Kneron’s innovative Real Facial Recognition solutions allow AI technology be quickly embedded into smartphones and accelerate the popularity of face unlocking applications. We look forward to working with Kneron to promote the solutions to the global market and popularizing the face unlocking function to make it a feature that everyone can use.”

Kneron Real Facial Recognition solutions integrate sophisticated facial recognition and deep learning technologies, which can recognize a real face within 0.2 seconds, with less than 0.0001 error rate. Additionally, one device can recognize several faces. Kneron Real Facial Recognition solutions include three technical versions: optical sensing analysis, biological behavior recognition, and background depth detection. Optical sensing analysis can determine whether a face is three-dimensional through analyzing the lighting variations on the face; biological behavior recognition integrates behavioral detection, such as eye blinking, to determine whether a face is real; the background depth detection solution can be used if there is an autofocus function in smartphone’s front camera. It can analyze the scene depth of field to avoid unlocking by a two-dimensional image.

This article was originally published on www.asiaone.com and can be viewed in full

(0)(0)