Recognito
  • About RECOGNITO
  • Face Recognition SDK
    • Performance Overview
    • Integration Guide
      • Linux
        • Installation
        • API Reference
        • Licensing
        • Sample Application
      • Windows
        • Installation
        • API Reference
        • Licensing
        • Sample Application
      • Android
        • Installation
        • API Reference
        • Licensing
        • Sample Application
      • iOS
        • Installation
        • API Reference
        • Licensing
        • Sample Application
      • Flutter
        • Installation
        • API Reference
        • Licensing
        • Sample Application
  • Face Liveness Detection SDK
    • Performance Overview
    • Integration Guide
      • Linux
        • Installation
        • API Reference
        • Licensing
        • Sample Application
      • Windows
        • Installation
        • API Reference
        • Licensing
        • Sample Application
      • Android
        • Installation
        • API Reference
        • Licensing
        • Sample Application
      • iOS
        • Installation
        • API Reference
        • Licensing
        • Sample Application
      • Flutter
        • Installation
        • API Reference
        • Licensing
        • Sample Application
  • ID Document Recognition SDK
    • Performance Overview
    • Integration Guide
      • Linux
        • Installation
        • API Reference
        • Licensing
        • Sample Application
      • Android
        • Installation
        • API Reference
        • Licensing
        • Sample Application
      • iOS
        • Installation
        • API Reference
        • Licensing
        • Sample Application
  • ID Document Liveness Detection SDK
    • Performance Overview
    • Integration Guide
      • Linux
        • Installation
        • API Reference
        • Licensing
        • Sample Application
  • License Option
  • How to implement 1:N identification with RECOGNITO SDK
  • Contact & Support
Powered by GitBook
On this page
  • Technology evaluation in NIST FRTE 1:1 Verification
  • FALSE NON-MATCH RATE (FNMR)
  • Summary FNMR value in FRTE 1:1
  • Comparison of FNMR values ​​according to dataset
  • - Dataset: VISA vs BORDER | FNMR @ FMR = 0.000001
  • - Dataset: VISA | FNMR @ FMR = 0.000001
  • - Dataset: MUGSHOT | FNMR @ FMR = 0.000010
  1. Face Recognition SDK

Performance Overview

NIST FRTE Top 1 Face Recognition Algorithm

PreviousAbout RECOGNITONextIntegration Guide

Last updated 5 months ago

In Face Recognition Vendor Test (FRVT) | NIST (National Institute of Standards and Technology), RECOGNITO's facial recognition algorithm scored among the top algorithms in both 1:1 verification and 1:N identification scenarios.

In particular, the recognito-001 algorithm currently ranks Top 1 in NIST FRVT 1:1 verification performance.

FRVT used 1999 to 2023 is being retired.

FRVT has been rebranded and split into FRTE (Face Recognition Technology Evaluation) and FATE (Face Analysis Technology Evaluation).

Technology evaluation in NIST FRTE 1:1 Verification

RECOGNITO algorithm(recognito_000, recognito_001) ranked Top 1 in NIST FRTE 1:1 verification performance among 570 vendors.

The table shows the top performing 1:1 algorithms measured on false non-match rate (FNMR) across several different datasets.

FALSE NON-MATCH RATE (FNMR)

FNMR is the proportion of mated comparisons below a threshold set to achieve the FMR given in the header on the fourth row. FMR is the proportion of impostor comparisons at or above that threshold. The light grey values give rank over all algorithms in that column.

Summary FNMR value in FRTE 1:1

The 3rd column is summary FNMR value (so that readers can look at the more accurate algorithms first)

Comparison of FNMR values ​​according to dataset

- Dataset: VISA vs BORDER | FNMR @ FMR = 0.000001

The test was performed by comparing high-quality images from the VISA dataset against lower quality images from the BORDER dataset. Both datasets include subjects from more than 100 countries, with specific imbalances due to visa issuance patterns and border-crossing demographics correspondingly.

RECOGNITO algorithm accuracy in this scenario was 0.16% FNMR (Top1) at 0.0001% FMR.

- Dataset: VISA | FNMR @ FMR = 0.000001

The dataset represents typical photos of US visa applicants. The face images are generally high quality. Part of the images are live capture and the other part is photographed from paper photos.

RECOGNITO algorithm accuracy in this scenario was 0.06% FNMR (Top1) at 0.0001% FMR.

- Dataset: MUGSHOT | FNMR @ FMR = 0.000010

The dataset represents typical photos of suspects taken by law enforcement officers. The photos were taken in a controlled environment thus their quality is high.

RECOGNITO algorithm accuracy in this scenario was 0.21% FNMR (Top1) at 0.001% FMR.

RECOGNITO Face Recognition Algorithm also has been tested by hundreds of our Partners & Customers.

FALSE NON-MATCH RATE (FNMR)
Summary FNMR value in FRTE 1:1
Dataset: VISA vs BORDER | FNMR @ FMR = 0.000001 and Algorithm (Submission Date)
Dataset: VISA | FNMR @ FMR = 0.000001 and Algorithm (Submission Date)
Dataset: MUGSHOT | FNMR @ FMR = 0.000010 and Algorithm (Submission Date)
FRTE 1:1 Performance Latest Update [2024-04-17]
FRTE 1:1 Performance Latest Update [2024-04-17]