Cognitec's products incorporate state-of-the-art technologies relevant to working with facial images, in particular deep learning, computer vision, and pattern recognition technologies. Algorithmic optimization since 1995 has resulted in superior independence from facial variances such as pose, mimic, age variance, different hair styles, glasses or temporary lighting changes.
Customers can license Cognitec's core technology, the FaceVACS Engine, through customized software development kits.
Highly focused and innovative R&D initiatives have again raised accuracy levels of Cognitec’s main matching algorithm and its age estimation technology. In addition, the latest versions are showing remarkably robust test results for facial images with masks.
We have released both matching algorithms B14 and A19 in version 9.6 of the FaceVACS Engine, with advanced deep learning methods and a new face finder contributing to substantial performance upgrades, in particular for facial images with masks, non-frontal poses beyond 30 degrees, and extreme mouth expressions.
The A19 version, with a smaller memory footprint, serves Linux-on-Arm and Android platforms.
The new face finder technology contributes to a five times higher detection rate for faces largely covered by facial masks.
The algorithm team has also upgraded the age estimator and underage detectors (18 or 21) for improved accuracy, using a new neural network that works on these three tasks simultaneously.
Please schedule a meeting with your account manager to discuss the performance test results in more detail!
Apache Log4j 2 Vulnerability
On December 9, GitHub disclosed a vulnerability with the highest-severity rating for the Apache Log4j 2, versions 2.0 to 2.14.1. Log4j is an open-source, Java-based logging utility widely used by enterprise applications and cloud services. A remote attacker could take control of the system.
Cognitec products do NOT use the log4j library, and are therefore not affected by this vulnerability.