TrueFace.AI introduces its facial recognition API with picture attack detection
TrueFace.AI has developed a solution designed to solve facial recognition’s vulnerability of not being able to distinguish between a living person’s face and a photo of the same individual held up in front of a face scanner, according to a report by Mashable.
Introduced last month on Product Hunt, TrueFace.ai is designed to detect “picture attacks.”
TrueFace.A initially developed the technology in 2014 to be used in customized smart homes, but later realized that their clients were using the solution more for security purposes.
“We saw an opportunity to expand our reach further and support use cases from ATM identity verification to access control for data centers,” said Shaun Moore, one of the creators of TrueFace.AI. “The only way we could reach scale across industries would be by stripping out the core tech and building a platform that allows anyone to use the technology we developed.”
TrueFace.AI can detect a face or multiple faces in a frame and distinguish 68 raw points for facial recognition.
Another key feature is spoof detection, which can differentiate between real faces and photos.
“While working on our hardware, we tested and used every major facial recognition provider. We believe that doing that (testing every solution available) and applying facial recognition to a very hard use case, like access control and the smart home, allowed us to make a better, more applicable solution,” said Moore. “All of these steps led us to understand how we could effectively deploy technology like ours in a commercial environment.”
The company developed the final product using deep learning, then trained classifiers with thousands of attack examples they had collected over the last few years.
TrueFace.AI offers a “freemium” plan to encourage the development community that helped spawn the solution, a $99 per month startup plan, and a $199 per month scale plan, as well as an enterprise plan via a custom agreement with TrueFace.AI.
Moore did not specify which companies are using the technology, but said that some of them are in the banking, telecommunications, and healthcare industries.