CyberLink is a world leader in facial recognition and face attribute technologies. FaceMe® is a highly accurate AI engine – ranked one of the best in the NIST Face Recognition Vendor Test (VISA and WILD tests). Through constant innovation, we ensure our technology meets the highest accuracy and security standards, for deployments across a wide range of industries and use cases. For over 20 years, CyberLink has built a stellar reputation in the IT industry for its R&D leadership.
FaceMe® is uniquely positioned to integrate edge-based AI facial recognition into a wide range of IoT solutions. FaceMe® is optimized to run on most hardware configurations, from high-end workstations to low-power chipsets typically used in IoT devices. It is compatible with Windows, Linux, Android and iOS systems.
FaceMe® provides system integrators with fast, flexible, and precise facial recognition SDK solutions. The convenient interface supports HTTP, C#, and C++ makes it both friendly and flexible to deploy FaceMe® across a wide range of scenarios, including: security, access control, public safety, smart retail and home protection.
Based on machine learning and deep neural network, FaceMe® has an accuracy rate (TAR, True Acceptance Rate) of 99.7% at 10-4 FAR. It ranks amongst the most precise and fastest facial recognition engines in the NIST’s Face Recognition Vendor Test (FRVT).
Built for Windows, Linux, Android, and iOS, FaceMe® is the ideal for cross-platform development solutions. It can be deployed across various applications, such as door security systems, digital signage, kiosks, POS systems, Android/iOS-based apps, and hybrid environments.
With flexible settings to control speed, accuracy and CPU processing, FaceMe® is optimized for servers and edge computing devices in various scenarios and hardware configurations.
To meet specific performance requirements of mainstream to high-end use cases, developers can choose to enable GPU acceleration, harnessing OpenVINO™, NVIDIA® CUDA™, Intel® Movidius™, Jetson™, ARM, and more to speed up deep-learning algorithms.
CyberLink’s unique TrueTheather™ visual enhancement technology improves image quality in the pre-processing phase and increases accuracy by 11.65%.
Multiple methods of anti-spoofing technology provide highly secure, accurate liveness detection to protect against biometric fraud, e.g. replay attack and print attack. FaceMe® supports anti-spoofing with mainstream 3D cameras as well as 2D cameras on phones and tablets.Watch Video
Combining U Alerts with FaceMe® enables automated notifications to mobile devices and PCs. When, for example, a registered visitor or VIP, a person of interest or even an intruder’s face is captured by a camera, U Alerts can send a message with a picture and short video recording to the relevant hosts, employees, or security guards, so they can take immediate action. U Alerts is derived from CyberLink’s U Messenger, a comprehensive business communications solution.
Generate highly precise location for faces detected within an image. Each face can be stored for further analysis and referencing.
Pinpoint up to 106 high-key facial points, allowing developers to create animated 3D models.
Quickly identify individuals from a database based on face detection results.
Instantly analyze face attributes, including age, gender, emotion and head orientation.
|May. 20, 2020||CyberLink Partners with Advantech to Enable FaceMe® Facial Recognition for Retail, Hospitality and Security AIoT Applications|
|May. 19, 2020||CyberLink’s FaceMe® Security AI Facial Recognition Announces Partnership with ASA Computers for Smart Visitor Management|
|Apr. 23, 2020||CyberLink FaceMe® Enables Facial Recognition on NEC’s All-in-One Personal Computers|