Exadel updates open-source facial recognition service for UI, easier CCTV deployments
Silicon Valley-based software consultancy and engineering provider Exadel has added a slew of features to its CompreFace open-source facial recognition service that aim to smooth out the customer experience and broaden its integration with other systems.
An initial version of CompreFace, a face biometrics app that uses deep neural networks, was released in November 2020 for a variety of industries like retail, hospitality and travel. Exadel released the 1.0 version to improve the user experience through its new user interface (UI), no-code options, ease of deployment, and additional integrations.
The updated UI manages subjects and images to commence facial collection without scripts or code. Exadel says it also helps resolve facial recognition problems by allowing users to check for correct images saved in each subject.
CompreFace now integrates facial recognition from closed caption television (CCTV) managed by the open-source home automation named Home Assistant. This addition allows CompreFace developers to write integrations that allow CCTV facial recognition without writing any custom code with the open-source library Double Take. It also connects Frigate, a network video recorder with real-time local object detection, to CompreFace for facial recognition. File server system unRAID is also given the option of integration using CompreFace and Double Take templates.
Serhii Pospielov, head of the AI practice at Exadel, says, “With the support of the developer community, Exadel has continued to improved the CompreFace user experience. As AI practices continue to rise, we are seeing more use cases emerge for facial recognition. This open-source service allows anyone to enter the facial recognition market and access highly reliable services without needing deep coding or machine learning experience.”