MicroFace SDK

Face Recognition Library for Embedded Systems.

Cross-platform face recognition library tailored for embedded targets. Compact algorithms for microcontrollers and edge devices — from detection to 1:N matching with templates under 148 bytes.

Live Demo
STM32N6
STM32N6 Cortex-M55 · NPU SRAM eMMC
CPU
–
RAM
–
Code
–
Idle
MicroFace SDK
Template 148 B
RAM peak < 2 kB
Latency 30 ms
_

Performance

Algorithms specifically designed to reduce library size and improve execution speed on embedded targets.

NXP i.MX 8M Plus

OperationTime
Face Detection20 ms
Feature Extraction30 ms
Template Matching0.01 ms

With dedicated NPU acceleration

Template & Accuracy

MetricValue
Template Size< 148 bytes
Score Range0 – 65535
NIST FRTETop Performer

Validated on civil & law enforcement datasets

Built-in Intelligence

Face Detection

Real-time face detection with FaceDetector optimized for low-power CPUs. Configurable confidence threshold from 0 to 100 for flexible use on embedded hardware.

Face Tracking

FaceTracker maintains continuous identity across video frames with automatic template updates, optimized for constrained real-time processing on embedded targets.

Feature Extraction

FaceEncoder generates compact face templates under 148 bytes — among the smallest on the market — enabling deployment on secure elements and microcontrollers.

Liveness Detection

FacePAD passive presentation attack detection guards against photos, videos and 3D masks. ColorPAD Model v4 runs efficiently on embedded CPU targets.

1:1 Verification

FaceMatcher.compareTemplates() returns a score from 0 to 65535 for reliable one-to-one face verification in access control and authentication scenarios.

1:N Identification

FaceIndexer enables ultra-fast one-to-many search with UUID-v4 support for large-scale identification on edge devices and local servers.

Core Technology

Optimized face recognition engine designed for embedded systems. The same validated algorithms as the Face SDK, tailored for microcontrollers and edge hardware with minimal footprint.

C
C++
C#
Python
Swift
Windows Linux macOS Android iOS STM32 i.MX 8M Plus

Affiliated Products

MicroFace Kit STM32H7

Starter kit for facial recognition on STM32H747 microcontroller platform at 400 MHz.

MicroFace Kit i.MX 8M Plus

Evaluation kit for facial recognition on NXP i.MX 8M Plus with dedicated AI acceleration.

MicroFace Kit STM32N6

Latest kit leveraging the STM32N6 neural accelerator for ultra-fast on-device recognition.

Developer Documentation

Comprehensive guides, API references and code samples to integrate the MicroFace SDK into your embedded application. Get started in minutes.

API Reference
Integration Guides
Code Samples
Visit Developer Portal
developer.id3technologies.com
import id3face as id3
 
id3.FaceLibrary.load_model(models_dir,
    id3.FaceModel.FACE_DETECTOR_4B)
 
detector = id3.FaceDetector(thread_count=1)
encoder  = id3.FaceEncoder(thread_count=1)
matcher  = id3.FaceMatcher()
 
image = id3.Image.from_file("face.jpg")
faces = detector.detect_faces(image)
tmpl  = encoder.create_template(image,
    faces.get_largest_face())
score = matcher.compare_templates(tmpl, ref)

Pricing

Choose the plan that fits your project. All plans include access to our developer portal and documentation.

Evaluation

Free

Try the SDK with no commitment.

  • 60-day trial
  • Limited API calls
  • Community support
  • Single platform
Get Started
Popular

Professional

Contact us

For production-ready integrations.

  • Unlimited API calls
  • All platforms
  • Email support
  • 1-year license
Contact Sales

Enterprise

Contact us

For large-scale deployments.

  • Volume licensing
  • Priority support
  • Custom integration
  • SLA guarantee
Contact Sales