Independent Vendor Tests
continue to prove the premier accuracy and speed of our face matching algorithm
Cognitec Systems regularly participates in renowned vendor tests for independent performance validation.
FRTE 1:N Identification
NIST published test results in December 2023 that include Cognitec’s latest matching algorithm submission, designated as cognitec-007. In most sub-tests, the reports exhibit significant accuracy improvements over the previous Cognitec submissions. A large impact on the improved results has a decreased failure-to-enroll rate (FTE), rewarding research and development efforts to improve face and landmark finders. The latest Cognitec algorithm still offers an excellent accuracy-speed trade-off compared to main competitors.
FRTE 1:1 Verification
The December 2023 NIST test results include Cognitec’s latest matching algorithm submission, designated as cognitec-005. In most sub-tests, the reports exhibit significant accuracy improvements over the previous Cognitec submissions, along with excellent accuracy-speed trade-off. In addition, the algorithm shows very low variation of False Match Rates across demographic groups, attesting to the low risk of being falsely matched to another facial image of the same sex, age group and region of birth. In other words, Cognitec’s algorithm holds an outstanding position as one of the least biased face recognition technologies.
FATE Age Estimation and Verification
In 2025, Cognitec topped the leaderboard of average ranking for the accuracy of age estimation and verification technologies, according to the NIST FATE: Age Estimation and Verification report. The report includes test results of age estimation accuracy globally and across demographic groups (gender and geographic region). Averaging the rankings across two genders and all six regions, Cognitec currently achieves the second best rank overall.
Disclaimer
FRVT results do not constitute endorsement of any particular system by the U.S. Government. Download complete test results at face.nist.gov.
Use of proprietary databases
Cognitec’s algorithms are not optimized or trained on databases used for tests. Training and optimization are performed on internal proprietary databases which do not contain data from test databases. Consequently, Cognitec’s test results can be generalized to similar unknown sets of data.