SMARTFACE SmartFace Embedded

Facial Biometrics for OEM & Edge Devices

Watch webinar

SmartFace Embedded is the Innovatrics’ proprietary face recognition engine customized to be easily ported on any hardware.

SmartFace Embedded can efficiently run time-critical operations such as face detection, facial landmarks, and face template extraction through on-edge or on-chip processing.

Face Recognition for Edge & OEM Devices

SmartFace Embedded can process video streams with the ability to detect faces in large crowds or low light environments. It has been optimized for the recognition of covered and obscured faces from very low-quality inputs.

Utilizing a proprietary matcher, which is one of the fastest and most accurate according to NIST, our facial biometric system notifies a user of detected faces within a few milliseconds, as well as identification when searching through a large gallery of identities.

technology is accessible from smartphones

Making Every Camera Smart

Regardless of use case and solution architecture, SmartFace Embedded can operate on a wide range of hardware platforms with optimized performance and resource utilization.

With over 15 years of engineering experience, our solution can support smart cameras, edge devices, and industrial PCs, plus custom integration with various peripherals like smart glasses, access control, and time & attendance terminals, smartphones, tablets, and many others.

See performance
utilize sensor and camera independence

Key Features


SmartFace Embedded

Small footprint with high performance

SmartFace Embedded

Custom approach and portability

SmartFace Embedded

HW and SW agnostic

SmartFace Embedded

Flexible licensing

SmartFace Embedded

Integrated with Innovatrics SmartFace ecosystem

Edge-to-Cloud Face Recognition with SmartFace Ecosystem

Given our edge computing approach, a video feed can be pre-processed on the camera or the edge device in order to reduce the required network bandwidth and server resources needed at the central site.

Through our edge-to-cloud architecture, any system can be easily scaled and virtually support an unlimited number of cameras while protecting public spaces without missing a single important event. Moreover, SmartFace can utilize GPUs to enhance the performance of the entire system.

Edge-to-Cloud architecture of face recognition system

Tech Box

Separate neural networks for:

  • Facial detection
  • Facial landmarks
  • Face mask detection
  • Facial attributes
  • Face template extraction
  • Liveness check
  • People detection
  • Body parts detection

Inference on CPU or NPU/GPU

  • x86 and ARM CPU architecture supported
  • Ambarella SoC, Blaize SoM, and NVidia Jetson supported

Other tech specification

  • Lightweight C++/RUST stack
  • Customized deployment of neural networks
  • 1:N identification
  • Camera watchlist synchronization API
  • HW video decoding/encoding
  • Real-time notifications over message queue (MQTT)

Performance


System-on-Chip

Face detection
(HD stream)
Facial
landmarks
Face template
extraction
Face identification
(1:10K)
Face Recognition for Edge and OEM Devices

Ambarella CV22

  • Quad-core ARM® Cortex-A53 CPU up to 1 GHz
  • 2 GB RAM
  • CVflow® computer vision processing
11 ms4 ms30 ms2 ms
SmartFace Embedded

Rockchip RV1109

  • Dual core ARM Cortex-A7
  • 1 GB RAM
  • Rockchip NPU
28 ms6 ms41 ms15 ms
SmartFace Embedded

NXP i.MX 8M Plus

  • Quad-core ARM® Cortex-A53 CPU up to 1 GHz
  • 2 GB RAM
  • NXP NPU
76 ms11,5 ms56 ms2,3 ms

System-on-Module

Face detection
(HD stream)
Facial
landmarks
Face template
extraction
Face identification
(1:10K)
face recognition on the edge

Blaize Pathfinder P1600 Embedded SoM

  • Dual-core ARM® Cortex-A53 CPU up to 1GHz
  • Up to 8 GB RAM
  • 16-core Blaize El Cano GSP
20 ms5 ms15 ms3.5 ms
face recognition on the edge

NVIDIA Jetson Xavier NX

  • 6-core NVIDIA Carmel ARM® v8.2 64-bit CPU
  • 8 GB RAM
  • NVIDIA Volta architecture with 384 NVIDIA CUDA® cores and 48 Tensor cores
12 ms3 ms20 ms1.5 ms
SmartFace Embedded

Hailo-8TM AI Processor

  • Intel® Pentium® Processor N6415 1.5M Cache, up to 3.00 GHz
  • 8 GB RAM
  • Hailo-8TM AI processor
14 ms3 ms15 ms1.8 ms
SmartFace Embedded

ONE-PAGER Facial Biometrics for OEM & Edge Devices

Download one-pager
BROWSE OTHER RESOURCES

SmartFace Platform datasheetDownload

Case studiesBrowse

WebinarsBrowse

One-pagersBrowse

Any questions?
Contact us!