Skip to main content
Version: 1.11.0 (latest)

Release notes

1.11.0 (23 May 2025)​

What's New​

  • ReferenceId column has been added to the "Applicants" report.
  • Attempt metadata has been expanded.
  • Added face crop display to the attempt page.
  • Added ability to create an index for Applicant columns.
  • Added the service to collect logs from web components.
  • Updated NPM packages related to the operation of the face recognition model (web component).
  • Added video format selection restriction for iOS, due to video rotation for webm format (web component).
  • Added logging of component operation to the server (web component).

Bug Fixes​

  • Fixed an error occurring when there were several identical motion control patterns in the system.
  • Fixed re-loading opencv.js if it already exists in html document (web component).
  • Fixed a bug that caused the web component to slow down on multiple consecutive attempts.
  • Fixed memory leak when releasing detector resources (web component).
  • Fixed a bug due to which the onMounted callback was not called when the component initialization was completed (web component).

1.10.0 (31 March 2025)​

What's New​

  • Updated SDK to version 3.25.0
  • Updated Kubernetes to version 1.32.2
  • Added registration confirmation mode
  • Added a mode to automatically calculate the size and position of the face frame based on face detection.
  • Added Unconfirmed status processing for the applicant.
  • Added error handling if face detector operation is not supported by the device.
  • Improved accuracy of head movement detection during inspections.

Bug Fixes​

  • Updated error message when attempting to download a deleted video due to storage expiration.
  • Removed applicant blocking during registration if risk is triggered.
  • Changed the text of an error that occurred when trying to download a deleted video due to expiration of storage time.
  • When registering, removed the blocking of the applicant if the risk is triggered.

1.9.0 (17 Feb 2025)​

What's New​

  • Introduced new metrics in the system performance report to track reasons for failed registration attempts.
  • Separated the face matching threshold into two independent values: one for registration and one for authorization.
  • Enabled registration of new BAF users.
  • Implemented email notifications for blocked applicants.
  • Added automatic applicant unlocking.
  • Introduced a public API endpoint for downloading the original image.
  • Restored the HTTP video recording option in web component settings.
  • Optimized frame size calculation logic for improved face positioning accuracy.
  • Removed the faceSettings field from the configuration.
  • Added a face border configuration object for Liveness Reflection and Motion Control.
  • Redesigned the user interface for Motion Control.
  • Added additional GIF-hints for Motion Control.
  • Added additional face position validation during Liveness Reflection recording.
  • Added new information blocks detailing Liveness Reflection and Motion Control checks (available in WebSocket and HTTP modes only).

Bug Fixes​

  • Adjusted video recorder log format: unexpected connection closures, timeouts, and canceled recordings now appear as Warnings instead of Errors.
  • Fixed database initialization jobs to ensure they wait for the database pod to start.
  • Fixed downloading photo attempts from the dashboard. Now the original image is retrieved instead of a compressed version.

1.8.0 (05 Dec 2024)​

What's New​

  • System Performance Reports: Added the ability to receive detailed reports with system performance metrics.
  • Liveness calculation results now include information about the detected attack type.
  • Introduced a new endpoint to get video-recorder service metrics in prometheus format.
  • Transport for data transfer in the web component has been changed from HTTP to WebSocket.
  • Flexible Check Configuration: Users can now customize the order of validation checks and disable Motion Control and Liveness Reflection (WebSocket only) in the web component.
  • Added the ability to overwrite settings received from the server via client-side configuration.
  • Added an error display in the web component when retrieving component setting fails.

Bug Fixes​

  • Resolved an issue where sorting by validationRequestId for RiskEvents in publicapi was incorrect.
  • Fixed an issue where face settings did not affect Motion Control validation in the web component.
  • Corrected a bug causing "Server Error" to be displayed instead of specific validation errors in the web component.
  • Fixed a slowdown issue triggered by repeatedly clicking the “Refresh” button in the web component.
  • Resolved an issue where multiple requests were made to access the camera in Telegram.
  • Fixed a bug where validation requests were executed before the server processed Liveness Reflection and Motion Control data when "autoSubmit" was enabled.
  • Fixed a problem causing the web component to hang on mobile devices when the browser session allowed camera access, but application permissions denied it.

1.7.0 (03 Sep 2024)​

What's New​

  • A setting for MassAttack risk parameters has been added to the dashboard.
  • The LRS logic has been split into two separate services. The Video Recorder is responsible for recording and saving attempts with video, while LRS is responsible for calculating liveness from the video.
  • Display of the applicant's "Reference ID" has been added to the dashboard.
  • Display of the risk list has been added in response to the "Validation" request.
  • Descriptions of attempt statuses have been added to the dashboard.
  • Added a setting to limit the number of simultaneous WebRTC connections.
  • Added a setting to disable video recording for performance improvement.
  • Added the ability to record video via HTTP requests.
  • Added a request to retrieve an applicant by Reference ID.
  • Added configuration of web components on the server.
  • The configuration has been updated:
    • Added the fingerprintWaitTime field.
    • lrsToken has been replaced with videoRecorderToken.
    • lrsDecryptKey has been replaced with videoRecorderDecryptionKey.

Bug Fixes​

  • Fixed handling of the photo liveness calculation error where negative score was saved.
  • Fixed display of attempt statuses in dashboard.
  • Fixed a bug in Web component where the Liveness check did not start when the value of timeToStartRecord was set to 0.
  • Fixed a bug in Web component where a processing message was displayed, making it impossible to continue working with the component.
  • Fixed a bug in Web component where a processing window was displayed indefinitely after passing Motion Control.

1.6.0 (01 Jul 2024)​

What's New​

  • Facial Recognition Subsystem (OMNI Platform) version updated to v1.18.0.
  • Added matcher module for OMNI Platform.
  • Added the ability to customize the prefix of buckets to the LRS chart.
  • Added functionality to save links to similar applicants in a attempt.
  • Added functionality to manage blacklists in the dashboard.
  • Expanded description of errors that may occur during attempt processing.
  • Added new risk UntrustedDevice.
  • Updated the existing export of data of all attempts of applicants in the dashboard.
  • Added pagination to export all applicants and all attempts of an applicant in the dashboard.
  • Added export of individual attempt data in dashboard.
  • Added face thumbnails for registered applicants in dashboard.
  • Critical changes: scores in the validations block are now written in decimal format and in the range from 0 to 1.
  • Added ability to manage active risks in dashboard settings.

Bug Fixes​

  • Attempts with server error will get the status: "server error" instead of "data invalid" as it was before.
  • Fixed CreatedTo filter of triggered risks and attempts metadata.
  • Fixed a sorting issue that could occur after transitions between pages in the dashboard.
  • Fixed an issue with photo selection in the applicant manual registration form in the dashboard.

1.5.0 (23 May 2024)​

What's New​

Bug Fixes​

  • Fixed behavior of "Number of Days Images to be Stored" setting in the dashboard. Now it affects all applicants.
  • Fixed display of triggered risks in dashboard. Now only those affecting the attempt are highlighted.

1.4.0 (19 Apr 2024)​

What's New​

  • Added counting of registration attempts when using a face photo.
  • Added cross-matching functionality.
  • Updated the interface of the attempt validation data in dashboard.

Bug Fixes​

  • Fixed applicant update button in the dashboard.
  • Fixed the value of the successAttempt field when requesting applicant data. Now it contains the last successful attempt.
  • Fixed the logic of applicant closure.

1.3.1 (29 Mar 2024)​

What's New​

  • Updated a module for cluster installation.

Bug Fixes​

  • Fixed a script for installing Kubernetes packages.

1.3.0 (05 Mar 2024)​

What's New​

  • Added optional frontend module for OMNI Platform.
  • Added implementation of Liveness Reflection algorithm.
  • Added extended minio settings for LRS service.
  • Added description of invalid data status reasons on dashboard.

Bug Fixes​

  • Fixed a list of settings displayed when getting an applicant by uuid.

1.2.0 (21 Feb 2024)​

What's New​

  • Facial Recognition Subsystem (OMNI Platform) version updated to v1.17.0.
  • Added endpoint for video download to publicapi.
  • Added showing of triggered risks in the dashboard even if their effect on the attempt is turned off.
  • Added endpoint to publicapi to update applicant information.
  • Added quality threshold setting.
  • Updated export of applicant data in dashboard.
  • Added showing of attempt metadata in dashboard.
  • Updated the name of downloaded photos in the dashboard.
  • Reduced the list of required fields when creating an applicant.
  • Updated time display in the dashboard. Now the time is displayed in the user timezone.
  • Add updated settings section.
  • Error format has been unified, each error has been assigned a code.
  • Added ability to record motion control video.
  • Added ability to customize a set of motion control video.
  • Added UntrustedIp, InconsistentMetadata and MissingMetadata risks.

Bug Fixes​

  • Fixed mail case-sensitivity when creating an applicant.
  • Fixed export of data on applicant attempts from the dashboard.
  • Fixed link to documentation in the dashboard.
  • Fixed impact of liveness threshold on verdict.

1.1.0 (7 Dec 2023)​

What's New​

  • Facial Recognition Subsystem (OMNI Platform) version updated to v1.16.0
  • Added the ability to view the status of the last attempt in BAF Dashboard
  • Added ability to sort by last attempt date in BAF Dashboard
  • Facial Recognition Subsystem liveness algorithm has been updated
  • Added the Liveness Reflection service prototype (BETA, in this version just saving the video attempts from video stream without scoring)
  • Improved BAF Dashboard user interface

Bug Fixes​

  • Corrected redirects on demo page refresh

1.0.0 (3 Oct 2023)​

What's New​

  • Updated OMNI Platform version to v1.15.1
  • Updated DVS version to v1.2307.04.3
  • Updated version of WebComponent tdv/onboarding to v2.2.27
  • Updated version of WebComponent tdv/idvc to v2.7.4
  • Added the ability to view face images in BAF API
  • Added the ability to view face images in BAF Dashboard
  • Added the ability to download images to BAF Dashboard
  • Optimized product installation
  • Completed transition to PostgreSQL

Bug Fixes​

  • Fixed display of liveness assessment results in BAF Dashboard (verdict + algorithm confidence)
  • Adjusted face match confidence threshold: 0.90