Meet us at CES 2025 in our suite at the Venetian — Contact us

Fast and accurate Familiar Face Identification for the smart home. Try it live!

Plumerai Familiar Face Identification accurately and efficiently recognizes household members and strangers. Our tiny and fast software runs directly within the camera. Trained on 30 million images and videos, the AI ensures high-accuracy identifications under any circumstance.

Documentation

SINGLE CORE ARM CORTEX-A

12 frames⁄s

WITH A TINY FOOTPRINT

5 MB

Functionality

  • Identifies individuals and strangers, even from a distance.
  • Offers both automatic and manual enrollment options.
  • Industry-leading accuracy: very few missed or incorrect identifications.
  • Detects strangers to reliably enable appropriate security responses.
  • Supports indoor, outdoor, and cameras with night vision
  • Detection distance exceeding 10m / 30ft.
  • Trained with 30 million labeled images and videos.
  • Validated across diverse demographics and environments.
  • Supports lenses with up to 180-degree field of view.

Deploy anywhere. Run on any device, with minimal resources.

Arm Cortex-A

  • Latency: 83 ms (single core)
  • Binary size: 5.5 MiB total

Arm Cortex-M + NPU @ 500MHz

  • Realtek Ameba Pro2 SOC
  • Latency: <100 ms

Arm Cortex-M85 @ 480 MHz

  • Renesas RA8 MCU
  • Latency: 250 ms

Arm Cortex-A55 @ 1200 MHz

  • Renesas RZ/V2L MPU
  • Latency: 55 ms

Arm Ethos-U55 @ 400 MHz

  • Alif Semiconductor Ensemble
  • Latency: 26 ms

Processor support

  • Arm Cortex-A with/without Neon
    • Cortex-A5, A7, A9, A53, A72, etc
    • Ambarella, SigmaStar, Realtek
    • Snapdragon, NXP i.MX, TI Sitara
    • Raspberry Pi
  • Arm Cortex-M with/without Helium
    • Arm Cortex-M33, M4, M7, M55, M85
  • Arm Ethos-U55/U65
  • x86 SSE2, SSE4, AVX, AVX2, AVX512
    • Intel Celeron, i3, i5, i7, Xeon, etc
    • AMD Opteron, Ryzen, Epyc, etc
  • ESP32-S3, RISC-V, ARC EM, ARM7, ARM9
  • Various NPUs and accelerators

Operating systems

  • Linux: x64, 32-bit Arm, 64-bit Arm
  • Windows: x64, 32-bit Arm, 64-bit Arm
  • MacOS: x64, 64-bit Arm
  • RTOS: FreeRTOS, others
  • Bare metal

Library APIs

  • C++
  • C
  • Python

Get access to the Plumerai Familiar Face Identification library.

Integration into your camera is easy with our C++ and Python APIs.

Thank you for submitting the form. We’ll get in touch as soon as possible.

There was an error submitting the form. Please try again later.

Automatic and manual enrollment

Our Familiar Face Identification supports both automatic and manual enrollment. With manual enrollment users scan their face using a mobile app. With automatic enrollment there is no explicit face scanning. Individuals are automatically enrolled after they come into view of the camera. Afterward, users can tag familiar faces in the app with a name. To see the difference, check out our automatic and manual enrollment demos.

Video doorbells and smart home cameras

Adding our Familiar Face Identification to smart home cameras enables new features that give the end customer peace of mind and enhance the user experience. Users can receive a message when a child comes home, filter video clips based on the person that's in the clip, and receive more relevant notifications. Since all the AI runs inside the camera, privacy is warranted and there's no cloud compute cost.

There are many possible applications. For example, a smart coffee machine that automatically offers to repeat your previous order, or a video conferencing system that identifies who's in the room.