The fruit of a close collaboration between the ASUS IoT and CyberLink’s FaceMe team, this joint solution provides ready-to-use, fully integrated facial-recognition capabilities for security, access control, visitor management and contactless experiences for retail, public services, hospitality and more.
CyberLink’s FaceMe SDK is a cross-platform AI facial recognition engine and ranked as one of the most accurate in the world. Offering a comprehensive operating systems support and optimized for IoT hardware and AI inference engines, FaceMe provides IoT/AIoT developers and system integrators highly accurate and flexible facial recognition capabilities, enabling a wide range of solutions applicable across industries.
ASUS IoT Tinker Board 2 is an Arm-based single-board computer that supports the Android 10 operating system. Powered by a six-core Rockchip RK3399 system-on-a-chip (SoC) with the new 64-bit Armv8 architecture, plus multi-core Mali-T860. Tinker Board 2 provides outstanding performance, rich wired and wireless connectivity, and dual 4K screen output support, making it ideal for deployment as a ready-to-use solution for digital signage, kiosks, point-of-sale (POS) and access-control systems for retail, public services, hospitality and healthcare.
“Facial recognition is one of the most popular technologies powering an exponentially growing set of IoT solutions in a booming market,” said Dr. Jau Huang, CEO of CyberLink. “We are honored to partner with ASUS, a world leader in computer hardware for IoT, and provide solutions developers with FaceMe, one of the most accurate and flexible facial recognition SDK in the world.“
“Edge AI is now a key piece of future technology in AIoT applications in various markets,” said Kuowei Chao, general manager of the ASUS IoT business unit. “ASUS IoT is thrilled to be collaborating with CyberLink, a world-leading AI facial-recognition technology company, by integrating solutions with Tinker Board 2, our powerful SBC that, compared with competing SBC products, offers significantly improved performance – making it ideal for retail, healthcare and security industries.”
Optimized for Arm-based SoCs and Android, FaceMe can deliver real-time face detection and extraction. The Face Recognition Edge AI Dev Kit, which includes both FaceMe and Tinker Board 2, can be deployed as a digital-signage solution to perform real-time face detection and precisely determine attributes such as age, gender and emotion, dynamically providing valuable data on visitor traffic that can be used for statistics or even real-time ad personalization. Alternatively, for example, the Face Recognition Edge AI Dev Kit can enable hotel check-in kiosks to instantly identify enrolled loyalty members and offer them fast, fully-personalized and contactless experiences.
CyberLink’s FaceMe engine is ranked as one of the most accurate facial recognition technologies in the world by the renowned National Institute of Standards and Technology’s Facial Recognition Vendor Test (FRVT), listed top 6 in both 1:1 and 1:N tests. With the comprehensive support for operating systems, including Windows, Linux (Ubuntu, Red Hat, CentOS), JetPack (Jetson), iOS and Android, and the optimization for CPU, GPU, SoC, APU, and VPUs, FaceMe provide a flexible solution to enable facial recognition across a wide range of IoT/AIoT devices.