FaceMe® | Optimization for NVIDIA | CyberLink
FaceMe®

FaceMe®

Optimization for NVIDIA® IoT Technologies

FaceMe® - Optimized for NVIDIA® IoT Technology

FaceMe®, a leader in facial recognition technologies, is designed for a wide range of IoT and AIoT applications and can be integrated with high-end servers, workstations and personal computers equipped with GPU to provide highly efficient performance. FaceMe® is optimized for TensorRT and supports a wide range of NVIDIA technologies, including CUDA and Jetson.

Customer Applications

Servers & Workstation

PCs

IoT Edge Devices

GPU & IoT Platform

  • Jetson Orin
  • Jetson Xavier
  • RTX

Inference Engine & OS

  • NVIDIA® Metropolis Certified (T4)

    FaceMe® is certified by the NVIDIA Metropolis Partner Program, an edge-to-cloud platform connecting system integrators with software solutions. CyberLink's FaceMe® technology can uniquely utilize NVIDIA's GPU lineup to enhance overall performance while providing flexible settings to control speed, accuracy and CPU processing. Developers can build high-performance solutions for the most demanding throughput and latency requirements.

Exceptional AI Facial Recognition Performance with FaceMe®

As an NVIDIA preferred technology partner, CyberLink’s FaceMe® SDK and FaceMe® Platform products, as well as FaceMe® Security turnkey software solution, are enhanced with NVIDIA’s powerful AI acceleration computing capabilities. By optimizing for NVIDIA hardware, including GPUs and Jetson Orin edge devices, CyberLink delivers remarkably accurate and fast facial recognition solutions.

FaceMe® Security Performance on NVIDIA® GPU

FaceMe® Security achieves the fastest facial recognition through leveraging the high performance computing of NVIDIA® GPUs. FaceMe® Security adds facial recognition to IP security cameras, and fully utilizes NVIDIA® GPU’s AI acceleration, helping lower customers total cost of ownership.

Visitor Traffic
Hardware
NVIDIA RTX A2000 (12GB)
NVIDIA RTX A5000 (24GB)

510

People per hour per channel

17 Channels

(Total 8,670 people/hour)
 

30 Channels

(Total 15,300 people/hour)
 

Visitor Traffic

510

People per hour per channel

Hardware
NVIDIA RTX A2000 (12GB)

17 Channels

(Total 8,670 people/hour)
 

NVIDIA RTX A5000 (24GB)

30 Channels

(Total 15,300 people/hour)
 

* 1080p (Full HD) video resolution with video frame rate of 15 fps

* Tested with Intel Core i7-12700K @ 3.61GHz CPU and 64 GB Memory

* Tested with FaceMe® Security 7.14.1 on 12/29/2023

FaceMe® SDK Edge Computing Performance on NVIDIA® Jetson

Nvidia® Jetson Orin enables FaceMe® SDK’s facial recognition engine to operate at amazingly fast speeds.

Autonomous machines and the market for embedded applications will continue to advance, and FaceMe® will be an invaluable tool for new edge computing products in retail and hospitality (ID verification), security (access control), and financial & insurance services (2-factor authentication).

Jetson Orin Dev Kit (2022)

Extraction Model
VH
UH
Execution Time (ms)
Detection + Extraction
7.7 ms
10.4 ms
Frames per second (fps)
129.3 fps
96.4 fps
Face Match Time (ms)
0.0021 ms
0.0041 ms
Memory Usage (MB)
4,500 MB
4,500 MB

Jetson Orin Dev Kit (2022)

Extraction Model
VH
UH
Execution Time (ms)
Detection + Extraction
7.7 ms
10.4 ms
Frames per second (fps)
129.3 fps
96.4 fps
Face Match Time (ms)
0.0021 ms
0.0041 ms
Memory Usage (MB)
4,500 MB
4,500 MB

* 1080p images, 1 face per image

* FaceMe® SDK - Jetson 6.12.0

Contact
Our Sales Team

Contact the FaceMe Team