The Biometric Open Protocol Standard (BOPS) provides three application-programming itrface (API) calls to support biometric identifcation and authentication including liveness. The BOPS implementation allows the systems to meet security needs by using the API. The BOPS implementation need not know whether the underlying system is a machine learning model, a relational database management system (RDBMS),or a search engine. The BOPS implementation functionality offers a“point- and-cut” mechanism to add the appropriate security to the production systems as well as to the systems in development.
Additionally, BOPS includes the biometric identification that the industry frequently calls the“one-to- many” (I:M) case. In the past, biometric identifcation was not considered because it requires a lookup against previously stored biometrics and this lokup required indexing and storing the biometric in plain text biometric identification. This specification includes biometric identification by using biometrice features vectors as input to the enroll endpoint, biometric feature vectors as input to the predict endpoint, and either video or audio as input to the liveness endpoint.
