Canadian biometrics firm Applied Recognition says its new technology sets a 'new benchmark' for face recognition accuracy.In a statement, the firm announced that it has reached the 0.2% threshold for Cross-Over Error Rate (CER) in testing against the FERET dataset maintained by the US National Institute of Standards and Technology for facial recognition systems evaluation. The CER observed when a technology is tuned such that its 'false positive rate' equals its 'false rejection rate' is the best summary measure of face recognition technologies' efficacy.The firm said that upgrades to Applied Recognition's core face recognition methods that enable this new level of performance are based on advanced machine learning techniques: residual networks are used to generate face vectors and face-to-face comparisons are processed using advanced statistical techniques.All ARI's SDKs and the line of “Ver-ID” applications will benefit from this update. Ver-ID Credentials, for example, establishes a person's identity by verifying the validity of a government issued photo ID then comparing the photo on the ID to an in-session “selfie”. ARI's liveness-detection technology ensures that the person whose is authenticating against the photoID is in fact the person requesting verification.”This latest advance in accuracy will further broaden the number of applications where face recognition is the dominant choice to achieve a high degree of security while enhancing customer experience”, said Ray Ganong, Co-CEO of Applied Recognition. “This new level of accuracy supports a completely automated workflow for financial transactions, such as opening a bank account or applying for a loan. Stringent identity verification requirements can be met to facilitate transactions that previously had to take place “face to face”. When combined with other methods of identity verification, such as credit checks and cell phone number verifications, the false authentication rate can be reduced to 1 in 10 million and without the need to route many bona fide applications through exception processes.””We now offer our customers 'the best of both worlds'”, according to Don Waugh, Co-CEO. “Looking back, developers seeking high-accuracy face recognition needed to rely on cloud-services with all the attendant problems: privacy concerns, latency, and reliance on a persistent Internet connection. Our technology's accuracy now substantially exceeds that of popular cloud-services while running directly on users' mobile devices or personal computers at sub-second speeds”.