“FindFace” ,a face recognition Intelligence algorithm by NTechLab

No one ahead in face recognition competition, In 2015 NTechLab algorithm won The MegaFace Benchmark challenge.

FindFace

NTechlab is doing the work that no body did before. This lab founded in 2015 by Artem Kuharenko doing great work on FindFace intelligence algorithm which equally behaves like human memory vision. Team NTechlab working on the neural network technology by the help of which they are developing smart and innovative software products in the field of face recognition.

FindFace

Every company has their prominent product which becomes a benchmark for the company so findFace is that quality product for NTechlab. FindFace is a website that lets users search for members of the social network VK(Vkontakte) by uploading a photograph, this site’s accuracy is about 70 percent. VK is popular social media site in Russia, possessing equal image to facebook. The one who registered their account in VK can find anyone else in findface just by uploading their pic.

The MegaFace Benchmark challenge

In the MegaFace Challenge launched by the University of Washington, researchers are working to improve the capabilities of facial recognition algorithms at the million person scale. More than 300 groups around the globe are working in this research but few of them got close to the challenge.

Many groups have achieved near-perfect accuracy rates, but this was done using a dataset of only 13,000 images, But most the group rate’s of accuracy in face recognition plummeted down when dataset scale extended up to millions of images due to the same identity of person at different age, different pose and different expression on faces.

Google's FaceNet was strongest on one test ¿ but it had dropped in accuracy, achieving 75 percent on the million person test. Russia's N-TechLab was strongest in another, at 73 percent. Other systems that had performed well on a small scale dropped to as low as 33 percent accuracy

Google’s FaceNet was strongest on one test – but it had dropped in accuracy, achieving 75 percent on the million person test, compared with its near-perfect scores with a smaller dataset. Russia’s N-TechLab was strongest in another, at 73 percent.

In 2015 NTechLab algorithm won The MegaFace Benchmark challenge.

NTechlab’s market value

Your face is your data identity and doesn’t try to indulge in any activity which directly harms your career, is messaged by NTechlab because many casinos, companies, and many government sectors are using this product mainly in Russia just to filter between fraud and real identity.

Russia’s Tinkoff Bank planning to use NTechlab’s product FindFace for their clients and after this they only need a selfie instead of generating the passcode for online banking, or to open an account and secure a loan online without showing a passport.

The Diamond Fortune company will install FindFace Cloud API in its casinos, technology catches the suspicious clients and also identify a person if they have visited the company’s casinos at least once before. Kukharenko added that “It will be possible to learn their habits and preferences, and to identify those guests who tend to spend more.”

Leave a Reply