SmartFace Cloud Matcher
The SmartFace Cloud Matcher is a lightweight, powerful, scalable, multi-platform and easy-to-deploy solution for facial biometrics use cases easily integrated to any third-party system via REST API. Available for fast cloud and on premise deployment.
It supports advanced identity management, identities enrollment, verification, identification, and liveness check.
Cloud Matcher Services
The SmartFace Cloud Matcher consist of following services that are based on the same technology that is used in the SmartFace Platform:
- Detection service is used for a detection of faces on incoming images
- Extraction service is used to generate biometric templates and extract age, gender and whether faces are covered by face masks
- Matching service is used for matching faces against watchlist members
- WatchlistAPI service provides the REST API
- Liveness service provides the liveness and spoof check
Listed services are based on the SmartFace Plaform services. The API in the Cloud Matcher contains a subset of API calls from the SmartFace Platform. Therefore an application that is making REST API calls to the Cloud Matcher can use the same API calls to get requests from the full installation of the SmartFace Platform.
There are additional services running as supporting services - dependencies:
- RabbitMQ service is the mandatory message broker orchestrating the SmartFace Cloud Matcher services communication
- MS SQL service running the MS SQL database, one of two SQL database options. Optional depending on the API endpoints needed.
- PG SQL service running the PG SQL database, one of two SQL database options. Optional depending on the API endpoints needed.
- Minio service running the NON-SQL database. Optional depending on the API endpoints needed.
- Jaeger service for tracing. Optional.
- PG admin service useful administration tool for PG SQL only. Optional.
The SmartFace Platform and its subset, the SmartFace Cloud Matcher store information in SQL - MS SQL service and PG SQL service and NoSQL database - Minio service . Structured data about events together with biometric templates are stored in the SQL database. Images of detected faces and full frame images of watchlist members are stored in the NoSQL database.
Not all endpoints need to have both SQL and NoSQL databases up and running. In the case you do not need to invoke and store the images of detected faces and the full frames of watchlist members you can avoid using the Minio database. For some endpoints, such as liveness / spoof check, not even a SQL database is needed. Currently, SmartFace Platform for Windows supports MS SQL 2016 and higher. For Linux distribution SmartFace Platform supports MS SQL 2016 and higher and Postgre SQL v.13.2 and higher. For NoSQL SmartFace Platform uses Minio DB.