See how it works
Facial Recognition AIoT Applications You Need to Know
Learn about Top Facial Recognition Use Cases in AIoT (Artificial Intelligence of Things)
Learn more>
A cross-platform facial recognition SDK with proven NIST accuracy, liveness detection, and flexible deployment across servers, edge devices, and mobile applications.
FaceMe® SDK, a cross-platform facial recognition engine, is uniquely positioned to integrate edge-based AI facial recognition into a wide range of IoT and AIoT solutions. FaceMe® SDK 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® SDK is top ranked in both NIST FRTE 1:1 and 1:N. In 1:1, FaceMe® provides up to 99.83% TAR (with FMR at 1E-6), which is ideal for use cases like eKYC and 2-factor authentication. In 1:N, FaceMe® reached 99.61% TAR on a 12-million-person mugshot database, ideal for use cases like security and surveillance.
1:1 Face Verification
VISA Category, Mar 2023
1:N Face Search
Mugshot Category, Investigation Mode, July 2024
Passive 2D Anti-spoofing
Video Convenience Category, Sep 2023
CyberLink’s accurate and reliable AI facial recognition engine, FaceMe® can be deployed across a wide range of IoT and AIoT devices including high-end workstations, PCs, mobile devices, digital signage, access control devices, POS systems, and kiosks. It’s versatile and supports major operating systems, AI inference engines, and multiple edge computing platforms. FaceMe® SDK processing speeds can also be accelerated with NVIDIA RTX GPUs.
Programming Languages
Operating Systems
Inference Engines
SoC & AI Platforms
Based on the test by NIST's Face Recognition Technology Evaluation (FRTE), FaceMe® achieves a 99.83% True Acceptance Rate (TAR) at an ultra-low one-in-a-million (1E-6) false acceptance rate (FAR). It ranks among the most precise and fastest facial recognition engines in the NIST FRTE.
FaceMe® demonstrated outstanding age estimation accuracy with a Mean Absolute Error (MAE) value of 2.87 in NIST's latest Face Analysis Technology Evaluation (FATE) Age Estimation & Verification.
FaceMe’s anti-spoofing technology has passed iBeta PAD Level 2 compliance testing, protecting against printed photos, video replay attacks, deepfakes, and other presentation attacks. It supports 2D webcams, 3D depth cameras, and IR+RGB camera modules, while detecting deepfake-based injection attacks and other threats involving virtual cameras, rooted devices, API hooking, and more.
FaceMe®'s updated algorithm provides the ability to accurately recognize a person's identity with up to a 98.21% accuracy rate, even when they are wearing a mask. It enables instantaneous and hygienic touchless biometric recognition.
FaceMe SDK extends recognition beyond facial identity with person attribute recognition and Person Re-ID. It detects clothing type, clothing color, and accessories for appearance-based search, while Re-ID re-identifies the same person across camera angles or time frames, even without seeing their face.
From remote customer onboarding to touchless building access and factory-floor authentication, FaceMe® powers facial recognition across finance, security, retail, surveillance, and manufacturing.
Replace cards and keys with facial recognition, the credential that can't be lost, forgotten, or shared.
Locate people of interest across an entire camera network in real time.
Touchless attendance and access. No badges. No buddy punching.
Authenticate operators and keep sites safe, even when users are wearing masks and safety gear.
Onboard and verify customers remotely, without the risk of identity fraud.
Recognize guests and shoppers to personalize experiences and improve every customer interaction.
Learn about Top Facial Recognition Use Cases in AIoT (Artificial Intelligence of Things)
Learn more>
UNIONCOMMUNITY integrated with FaceMe® SDK for facial recognition access control systems that feature enhanced capabilities to significantly increase security.
Book a Demo