BioID PhotoVerify enables automated online identity proofing
29 November 2017 16:09 GMT

German multimodal biometrics as a service firm BioID has announced the release of a PhotoVerify API as part of the BioID Web Service (BWS).

With this service, online providers can verify the legal identities of their customers and users without the need for registration in person or via live video session. 

The new API compares two live facial images against an image from a photo ID such as a passport or driver’s license, making sure that (1) the live images are truly from a live person, not a photo or video, and (2) the live person matches the ID photo. Since no biometric templates or photos are stored and all data is deleted after the operation, it fulfills all requirements for an anonymous identity proofing service. 

“Inconvenient registration and identification processes present a known barrier to adoption of a wide variety of online services, and anything companies can do to simplify these processes while remaining compliant with regulations serves to increase their user base,” said Ho Chang, BioID CEO. “With our new PhotoVerify API, we are happy to offer online services yet another strong tool for hassle-free identity management and authentication.” 

Until recently, applications requiring verification of a person’s legal identity have required appearing in person to present a photo ID. In some cases, this process is now carried out remotely via live video session, but this is still a costly and inconvenient process and often done by external service providers, adding further expense and complexity. Manual ID proofing is also subject to human error, because peoples’ appearances change from day to day and, for video-based processes, also due to poor-quality video streaming.

Advanced face recognition with built-in liveness detection now makes it possible to replace this manual process with faster, more convenient automated ID verification that is more economical and can be integrated into existing services with only a few lines of code.