What’s New in FindFace Multi 1.1

Meet FindFace Multi 1.1! This version will broaden the scope of your system’s functional and integrational possibilities and make it more ethical, secure, and usable.

New Features:

  • Areas: the innovative video analytics module allows you to monitor the presence of people in given areas, using specific rules and schedules.

    Possible use cases: long queues prevention at retail outlets, theft prevention at enterprises during non-working hours, hazardous area control, work time tracking.

    See Area Management.

  • Clothing type recognition: a new AI-based feature that allows you to automatically recognize upper and lower wear and headgear on a person.

    Possible use cases: crime prevention, hot pursuit for offenders, missing person search.

    See Enable Body and Body Attribute Recognition.

  • Distance measurement: a novel feature embedded into the Counters functionality that measures the distance between bodies.

    Possible use cases: monitoring public gatherings, crowding prevention, health protocol enforcement.

    See Face and Body Counters. Distance between People.

  • List of user sessions and blocklist: the new monitoring tool allows you to view user sessions and learn associated data, such as the connected device UUID, type of user interface (mobile app or web interface), IP address, last ping time, and so on. You can also blocklist a device without deactivating the user account.

    Possible use cases: prompt measures when a user’s mobile phone with the FindFace Multi mobile app installed has been stolen, system security intensification.

    See List of User Sessions. Blocklist.

  • Edge devices: the new integration method allows you to receive frames with objects from edge devices of any vendor. Once FindFace Multi receives a frame from an edge device, it will initiate the extraction of the object’s feature vector and event creation. You can work with these events by analogy with the events from CCTV cameras.

    Possible use cases: integration with Access Control terminals and edge devices of other types that produce frames.

    See Edge Devices.

  • Object blurring on Video Wall: a new feature that, once enabled, automatically blurs unmatched objects in the video displayed on the Video Wall. It is a final addition to make the system fully GDPR-compliant.

    Possible user cases: compliance with GDPR and similar laws of personal data protection.

    See Video Wall.

  • On-premise licensing via hardware fingerprint: the new licensing method allows you to license your FindFace Multi instance using a hardware fingerprint preliminarily taken via the Sentinel technology.

    Possible use cases: prompt offline licensing without the necessity for USB dongle shipping.

    See Offline Licensing via Hardware Fingerprint.

Fresh Neural Networks:

  • Clothing type recognition: a brand-new neural network clothes_type.v0 to recognize upper and lower wear and headgear.

  • Age recognition: a new version age.v2 with improved characteristics.

  • Car license plate recognition: a new version license_plate.v2 that supports UAE, Russia, Kazakhstan, Georgia, South Africa, Vietnam, Belarus, Ukraine, Armenia, and Kyrgyzstan.

  • Car image normalization: a new version anaferon.v1 for better performance.

Enhanced Algorithms, UI, UX:

System Safety:

  • Dossier: create the allowlist of file extensions to be uploaded to a dossier.