FaceMe® SDK - Cross-Platform Face Recognition Engine for AIoT/IoT Devices | CyberLink
FaceMe®

FaceMe®

The World’s Top AI Facial Recognition Engine

Top 10 in both NIST FRVT 1:1 & 1:N

What is FaceMe® SDK

  • 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.

  • See how it works Download Brochure

Top Listed in NIST FRVT 1:1 & 1:N

  • FaceMe® SDK is top ranked in both NIST FRVT 1:1 and 1:N. In 1:N, FaceMe® provides up to 99.83 TAR in VISA Border investigation mode, which is ideal for use cases like border check and eKYC. In 1:1 WILD photo, FaceMe® reached 96.98% TAR (with FMR at 1E-5), ideal for use cases like security and surveillance.

  • No. 1   in 1:N

    No. 6 when incl. China & Russia Vendors

    VISA Border 1:N

    Investigation Mode/1.6M DB

    TAR: 99.83%

    NIST FRVT 1:N Leaderboard, VISA Border Category, 2/9/2021
  • No. 1   in 1:1

    No. 6 when incl. China Vendors

    Wild Photo 1:1

    FMR: 1E-5 (0.00001)

    TAR: 96.98%

    NIST FRVT 1:1 Leaderboard, Wild Category, 1/19/2021

Optimized for IoT / AIoT Edge Devices and Application Scenarios

  • Cross-Platform

    facial recognition Windows facial recognition Linux facial recognition Android facial recognition iOS facial recognition Nvidia_JetPack
  • Multiple AI Inference Engines

    facial recognition OpenVINO facial recognition TensorFlow facial recognition TensorRT facial recognition CoreML
  • IoT/AIoT Platforms

    facial recognition Nvidia_Jetson facial recognition Intel_Celeron facial recognition Intel_Core facial recognition Intel_Xeon facial recognition iOS facial recognition ARM
  • GPU / VPU Hardware Acceleration

    facial recognition Nvidia_Quadro facial recognition Nvidia_Geoforce_RTX facial recognition Intel_Movidius

FaceMe® SDK Key Features

  • Face Recognition

    • Face detection
    • Facial template extraction
    • Face search
    • Face compare & match
  • Age, Gender, and Emotion Detection

    • Gender
    • Age
    • Facial expression
    • Head orientation
  • Anti-spoofing​​

    • Anti-spoofing with 2D camera
    • Anti-spoofing with 3D depth camera
    • TrueTheater enhancement
  • Face with Masks

    • Mask detection
    • Facial recognition through masks – TAR up to 98.21%

Outstanding AI Technology

  • Highly Accurate

    Based on machine learning and deep neural network, FaceMe® has an accuracy rate (TAR, True Acceptance Rate) of 99.83% at 10-4 FAR. It ranks amongst the most precise and fastest facial recognition engines in NIST's Face Recognition Vendor Test (FRVT).

  • Secure Anti-Spoofing

    Multiple anti-spoofing technologies 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
  • Facial Recognition When Wearing a Mask

    FaceMe®'s updated algorithm provides the ability to accurately recognize a person's identity with up to 98% accuracy rate even if they are wearing a mask. It enables instantaneous and hygienic touchless biometric recognition.

Use Cases and Applications:

  • System Integrators
  • Developers

Deploying FaceMe®

Facial recognition can enhance security, identify potentially fraudulent activities and help loss prevention. FaceMe®’s cross-platform SDK and flexible architecture enable an easy deployment in any environment.

  • Smart Security

    • Time & attendance
    • Access control
    • Smart ID kiosk
    • Smart pharmacy
  • Smart Facility

    • Door access system and identification
    • Event-based alert system
    • ID authentication for machinery use
    • Field entry clearance
  • Smart Retail

    • Transaction authentication
    • Customer demographics
    • Customer personalization
    • Access control and authentication
    • Loss prevention
  • Smart Banking

    • Identity verification
    • Fraud prevention
    • Transaction authentication
    • Forensic investigation

Integrating FaceMe®

FaceMe® supports a variety of operating systems and AI inference engines. It is designed to run on mainstream processors and is optimized to take advantage of GPU / VPU hardware acceleration. FaceMe®’s flexible and scalable architecture provides hardware and software developers the tools to create customized facial recognition solutions and experiences.

  • Hardware

    • Industrial computers
    • Workstations
    • Servers
    • Embedded systems
  • Surveillance and Access Control

    • IP cameras, Smart cameras
    • Video management systems
    • Automated doors and turnstiles
    • Time attendance systems
  • Retail and Financial

    • POS terminals and kiosks
    • Digital signage
    • Customer loyalty programs
    • ATMs
  • Other IoT/ AIoT

    • Mobile devices
    • Smart homes & buildings
    • Factories and production lines

Market Insights & Downloads

  • 5 Facial Recognition AIoT Applications You Need to Know
    5 Facial Recognition AIoT Applications You Need to Know
    Learn about Top 5 Facial Recognition Use Cases in AIoT (Artificial Intelligence of Things)
    2023/03/15
  • Building AIoT Devices for Facial Recognition
    Building AIoT Devices for Facial Recognition
    Learn about the key considerations for building an ARM-based AIoT device.
    2022/11/30
  • FaceMe SDK Brochure
    FaceMe SDK Brochure
    The World’s Top Cross-Platform AI Facial Recognition Engine
    2022/03/17
    PDF(0.7MB)
    Download
Contact
Our Sales Team
Contact the FaceMe Team