FaceMe® Enables Customers to Integrate Biometric Technology with MediaTek i350 AI Chipset Platform for AIoT devices
As a leading global brand with expertise in smart handheld devices, smart homes, wireless technologies and other connected solutions, MediaTek launched the i350 edge AI platform designed for mainstream AIoT applications that require vision and voice edge processing. The edge AI platform was built using an ultra-efficient 14nm process and incorporates a dedicated APU (AI processor) and DSP (digital signal processor) to enable computer vision and speech applications with greater performance and power efficiency across AIoT applications.
Read More: The Evolving Cyber Risks and Vulnerabilities in the Healthcare Industry
To support the MediaTek i350 edge AI platform, CyberLink’s FaceMe® facial recognition engine provides functionality for facial detection, recognition and feature extraction, capable of conducting identity verification in merely 0.12 second. Due to MediaTek’s NeuroPilot platform, the computing speed of FaceMe®, powered by deep learning algorithms, can be considerably increased. By utilizing the processing power of NeuroPilot, i350 provides up to three times performance gain for facial recognition and face attribute extraction. Biometric identification can be used for deployments across a myriad of industries and use cases, including security, access control, public safety, smart retail, point-of-sale, ordering machines, digital signage and home protection.
“The addition of biometric identification to AIoT creates an incredible opportunity to improve security and access control with edge devices,” said Dr. Jau Huang, CEO of CyberLink. “It’s our honor to join MediaTek’s AIoT ecosystem. Through the integration of FaceMe® and i350, system integrators will now have access to the most efficient yet low-power consumption applications with identity verification, providing a new class of industry infrastructure to move the biometric technology forward.”
Read More: Should Cybersecurity Training be Included in the Employee Onboarding Deck?
Based on machine learning and deep neural networks, CyberLink FaceMe® has an accuracy rate of 99.7%. It ranks amongst the most precise and fastest facial recognition engines in the United States’ National Institute of Standards and Technology Face Recognition Vendor Test (FRVT). Built for Windows, Linux, Android and iOS, FaceMe® is ideal for cross-platform solutions. It is optimized to run on high-end workstations with CPU or GPU to low-power chipsets typically used in IoT devices—capable of being deployed virtually anywhere
For more such updates follow us on Google News ITsecuritywire News. Please subscribe to our Newsletter for more updates.