Rank One Computing has launched a new periocular biometrics solution that is tailored for the age of COVID-19 and social distancing.
The company’s ROC Periocular algorithm is designed to identify an individual based on the eye and eyebrow regions of the face. It’s the product of AI learning based on deep convolutional neural networks, and Rank One says it can perform a biometric scan even faster than its ROC FR facial recognition algorithm.
That having been said, in a post on its company blog, Rank One explained that ROC Periocular’s enrollment speed “does not currently possess Rank One’s hallmark efficiency.” That’s because Rank One’s goal was to bring this solution to market as quickly as possible, given its applications during the COVID-19 pandemic. By identifying individuals based on their eyes and eyebrow regions, it can accommodate the increasing use of face masks in response to the COVID-19 threat.
The solution’s accuracy is still comparable to that of Rank One’s facial recognition algorithms circa early 2018, which means that “this periocular algorithm would have outperformed a large number of NIST FRVT face recognition algorithms two years ago,” the company said.
What’s more, the similarity of the ROC Periocular API to that of its ROC FR solution means that clients who are already using Rank One’s facial recognition technology can easily switch to periocular authentication, in some cases by changing just one line of code.
Rank One says it is planning to add further API features allowing clients to combine the ROC Periocular and ROC FR algorithms, which will enable even greater flexibility in authentication in the future.
May 7, 2020 – by Alex Perala