Moscow company VisionLabs have taken first place in the testing of facial recognition algorithms conducted of the National Institute of Standards and Technology of the United States.
The main goal of testing was to determine the most universal facial recognition algorithms that work equally well in a wide variety of application scenarios. Testing was carried out using several types of photos, from photographs to documents and pictures from webcams and phones.
The solution of the Moscow developer was recognized as the best in several categories:
Visa - studio photo for documents;
Border - pictures taken at passport control in airport;
Visaborder - comparison of images of the two previous categories;
Mugshot - “police photo” or a portrait for any card index.