Yesterday, Russian facial recognition company, FindFace released a service that allows users to search through 313 million active profiles on Twitter with just a picture. With so many fake profiles on Twitter, having a service that can quickly locate profiles that may be using your pictures without consent is a great feature.
Those aren't the only uses for the service, however. “FindFace will help Twitter users ensure their photos aren’t being used for fake accounts,” Ntechlab co-founder Alexander Kabakov explained. “On top of that, users can find people they knew previously, from old relatives to old relationships. When an exact match isn’t found, FindFace will identify the most similar matches instead.”
This isn't the first service to use the technology from NtechLab. FindFace first released for Russia's largest social network, VK, which has about 200 million active accounts. FindFace can identify faces with over 70% accuracy, extremely impressive considering how many pictures it is scanning through. The service will give you one account it believes matches best, but will also offer other suggestions.
When asked about bringing the service to Twitter, Kabakov added, "“We are excited to offer FindFace’s service to an even wider audience, especially for free. Many businesses are already enjoying the powerful facial recognition software. Twitter’s sizeable database represents a sizeable step in the adoption of facial recognition software for everyday use.”
Bringing the service to Twitter is a great move for FindFace, who also recently released FindFace.Pro. Pro is a service that allows other companies to use the powerful SDK and API in their own applications. By using the tech on Twitter, the company is helping secure a much bigger audience to hopefully attract clients interested in Pro.
All of this power really comes from NtechLab. NtechLab, winner of the Washington State "MegaFace" competition, beating out companies like Google, developed the system that allows FindFace to identify matches with such accuracy. Using a combination of machine learning and neural network architecture, the company offers some of the most advanced facial recognition software in the world.