First Steps after Deployment

Once you have successfully deployed FindFace, it is time to open the web interface and get started. In this chapter, you can find a recommended sequence of steps that will help you harness your system’s complete functionality.

In this chapter:

Gear Up for Work

Perform the primary configuration of your system:

  1. Set up the left side navigation bar.

  2. Adapt general preferences.

  3. Choose the language.

Create Users and Ensure System Security

  1. Check out the list of predefined user roles and create new roles if necessary.

  2. Add users to the system and grant them privileges.

  3. Configure authentication and user session monitoring. Authentication is possible by password, face, face or password, face and password.

You may also need:

  1. Enable SSL data encryption.

  2. Enable dossier security. If the dossier security is disabled, the dossier photos and attachments will be available by direct link regardless of the user rights.

  3. Disable FindFace ACL if you do not need it, as the constant permission checks consume a significant amount of system resources.

Organize Cameras

  1. Create a new camera group or use the default one. A camera group is an entity that allows you to group cameras subject to their physical location. For example, cameras at the same entrance to a building can be combined into one camera group.

  2. Add cameras to the camera group and check their statuses.

You may also need:

  1. Configure your system to process video from the group of cameras at their physical location. It may come in handy in a distributed architecture. Learn more.

  2. Consider enabling event deduplication if observation scenes of cameras within the group overlap. This feature allows you to exclude coinciding facial recognition events among cameras belonging to the same group. Learn more.

Organize Watch Lists and Dossiers

  1. Create a new watch list or use the default one. A watch list is an entity that allows you to classify people by arbitrary criteria: blacklist, wanted, VIP, staff, etc.

  2. Upload dossiers and add them in the watch list either manually, in bulk via the web interface, or use the console bulk upload function.

You may also need:

  1. Distribute dossier database among several hosts. The dossier database will be available for editing on the master server and reading and monitoring on the slaves.

  2. Customize dossier content. Create additional fields, tabs, and search filters.

Start Monitoring Faces

By default, FindFace is monitoring only unmatched faces. To enable a custom watch list monitoring, simply make this list active. You can also turn on sound notifications and request manual acknowledgment for the events associated with the list.

You may also need:

  1. Make events more informative by enabling recognition of gender, age, emotions, beard, face mask, and glasses. Learn more.

  2. Protect your system from spoofing by enabling the Face Liveness Detection functionality. Learn more.

  3. Support laws related to the processing of personal data of individuals (GDPR and similar). Learn more.

Organize Video Surveillance

Create a camera layout for essential video surveillance.

Start Counting Faces and Silhouettes

Set up counters to count faces and silhouettes on connected cameras. This functionality can apply to a wide range of situations, such as people counting in queues and waiting areas, monitoring public gatherings, crowding prevention, and more.

Start Analyzing People

FindFace provide a set of people-related analytical tools:

  1. Enable person recognition to build a person gallery. The system databases will hold a new entity person event linked to all episodes that feature a person’s face. You can work with the person gallery similarly as with events and episodes.

  2. Analyze social interactions. Examine a circle of people with whom a person has previously been in contact.

  3. View ‘know your customer’ analytics (KYC). It is analytics on the number of visitors, their gender, average age, most frequently visited zones, and the character of visits (first-timers or returners). Learn more.

FindFace in Action

  1. Automatically identify faces in live video and check them against watch lists. Work with the event history by using various filters.

  2. Harness the episodes. An episode is a set of identification events that feature faces of the same person, detected within a certain period. As events on the Events tab show up in an arbitrary order, a large number of miscellaneous events can make the work challenging and unproductive. With the Episodes, the system uses AI to organize incoming events based on the faces similarity and detection time. This allows for the effortless processing of diverse events, even in large numbers.

  3. Search for faces in the following databases:

  4. Search archived videos for faces under monitoring.

  5. Manually compare two faces and verify that they belong to the same person.

  6. Build detailed reports on face recognition events, episodes, search events, persons, counters, cameras, dossiers, and KYC analytics.

  7. Use the mobile app.

Basic Maintenance

  1. Configure automatic cleanup of events, episodes, and full frames.

  2. Manually purge events, episodes, and full frames.

  3. Regularly backup the database.

  4. Harness the FindFace comprehensive and searchable audit logs to enhance your system protection.

Go Further

  1. Set up webhooks to automatically send notifications about specific events, episodes, and counter records to a given URL. In this case, when such an event occurs, FindFace will send an HTTP request to the URL configured for the webhook. You can use webhooks for various purposes, for example, to notify a user about a particular event, invoke required behavior on a target website, and solve security tasks such as automated access control. Learn more.

  2. Harness the FindFace functions through HTTP API.

  3. Check out the list of our partner integrations.

  4. Harness plugins to set your directives that determine how FindFace processes detected faces.

See also