Unlike other facial liveness solutions on the market, ROC’s patented approach is entirely sensor and system agnostic, works with images and videos from any source, and returns a highly accurate liveness/anti-spoofing score in less than one second. As previously announced, ROC’s latest release of ROC SDK v2.3 significantly reduced the error rate of its patented, single-frame passive liveness solution by 2x to 5x across different spoof mediums and genuine user presentation categories as compared to its previous version.
According to ROC CEO Scott Swann, “We are proud and excited to have iBeta’s testing compliance as another validation of our growing ID Proofing solutions. Across a range of different facial spoofing techniques, ROC is now delivering better than 99% PAD / spoof detection accuracy. We will continue pushing our AI/ML expertise to deliver better and better ID Proofing solutions to secure the growing number of commercial and government services that are shifting online.”
ROC plans to submit its patented, single-frame liveness solution to the NIST FRVT PAD testing series, slated to begin in January 2023. The will continue to invest in improvements that provide users and partners with best-in-class solutions to conform with both ISO/IEC 30107-3 facial PAD standards and ISO/IEC 29794-5 Face Image Quality standards that will be measured in the forthcoming NIST FRVT Specific Image Defect Detection (SIDD) benchmark.
ROC’s approach is protected by US Patent US 10,839,251 B2 “Method and system for implementing image authentication for authenticating persons or items” since June 26, 2017. This foundational patent broadly covers any computer vision liveness approach that analyzes image regions to identify spatial relationships amongst pixels or groups of pixels.
Contact us to learn more!