The Russian N-Tech.Lab Company won the World Championship in Face Recognition titled ‘The MegaFace Benchmark’ organized by the University of Washington.

      The algorithm created by Russian developers was able to bypass more than 100 solutions from competitors, including Facenet program created by Google. This is stated in the message of the startup received by “Lenta.Ru”. The team of N-Tech.Lab created a unique algorithm based on the neural network technology (solutions based on the principle of organization and functioning of biological neural networks - nerve cells of a living organism), which allows to identify a set of individual features of a human face.

      Experts recognized the Russian solution as the most accurate one for databases with a volume of a million or more photos - recognition accuracy amounted to 3.3 percent. The second place in this category was taken by the solution by Facenet, and the third – by the algorithm proposed by the experts from Peking University.