In 2015 Neurotechnology face recognition engine integrated with face tracker was submitted to Face in Video Evaluation (FIVE) performed by the U.S. National Institute of Standards and Technology (NIST). FIVE was an independent public test of face recognition of non-cooperating subjects who are recorded passively and are mostly unaware to the presence of cameras.
This time our submissions did not correspond to any particular product version. It was an experimental early development version of our next generation face recognition algorithm, which, according to our internal tests, was improved significantly and later included into VeriLook SDK and MegaMatcher SDK. The false rejection rate was reduced 2-3 times depending on the type of images in the dataset. Nevertheless, in average the submitted algorithm was ranked among top 8 most accurate face recognition algorithms out of 16 vendors.
See the full FIVE report (PDF, 47 MB) at NIST website.