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.

FRVT 2019

Cognitec announced its successful participation in the NIST FRVT: Identification, confirming the solid market position of our matching technology, and the achievements of our algorithm research and development. The September 2019 results, comparing 203 algorithms from 51 commercial developers and one university, show Cognitec’s high performance in accuracy tests for large galleries of frontal mugshots and of unconstrained images (Wild).

FRVT 2018

Cognitec reported remarkable leaderboard positions in the Ongoing FRVT 1:1, ahead of all face recognition companies with established market presence and products. The November 2018 results, comparing 100 algorithms from 57 developers, show Cognitec’s high performance for accuracy tests with visa photos. In addition, Cognitec‘s template generation was the fastest among the highest ranking algorithms with false non-match rates lower than 0.01, at a false match rate of 0.0001.

FRVT 2013

Test results on the performance of automated age estimation algorithms confirmed Cognitec Systems’ leading position in the face recognition market. Test results show that Cognitec’s algorithm performs with the highest accuracy for all age groups. Most notably, the algorithm shows superior performance “in the youth and senior age groups, leading the next most accurate algorithm in 5-year accuracy by 30% and 16%, respectively,” according to the report.


FRVT and MBE results do not constitute endorsement of any particular system by the U.S. Government. Download complete test results at

Use of proprietary databases

Cognitec's algorithms are not optimized or trained on databases used for tests, like the FERET database. 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.