Face Recognition Performance
NIST FRTE Top 1 Face Recognition Algorithm
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.
Last updated
